APPARATUS AND METHOD FOR SELECTIVE MATERIAL REMOVAL DURING POLISHING BACKGROUND Field [0001] Embodiments of the present disclosure generally relate to chemical mechanical polishing (CMP) and, more specifically, to correcting thickness asymmetry during a CMP process. Description of the Related Art [0002] An integrated circuit is typically formed on a substrate by the sequential deposition of conductive, semiconductive, or insulative layers on a semiconductor substrate. A variety of fabrication processes require planarization of a layer on the substrate. For example, one fabrication step involves depositing a filler layer over a non-planar surface and planarizing the filler layer. For certain applications, the filler layer is planarized until the top surface of a patterned layer is exposed. For example, a metal layer can be deposited on a patterned insulative layer to fill trenches and holes in the insulative layer. After planarization, the remaining portions of the metal in the trenches and holes of the patterned layer form vias, plugs, and lines to provide conductive paths between integrated circuits (ICs) on the substrate. As another example, a dielectric layer can be deposited over a patterned conductive layer, and then planarized to enable subsequent photolithographic steps. [0003] Chemical mechanical polishing (CMP) is one accepted method of planarization. This planarization method typically requires that the substrate be mounted on a carrier head. The exposed surface of the substrate, the surface with the layer deposition, is typically placed against a rotating polishing pad. The carrier head provides a controllable load on the substrate to urge it against the polishing pad. A polishing slurry with abrasive particles is typically supplied to the surface of the polishing pad and spreads in between the substrate and the polishing pad. The polishing pad and the carrier head each rotate at a constant rotational speed and the abrasive slurry removes material from one or more of the layers. Material is removed in a planar fashion and the material removal process is symmetric about a central axis of the substrate. The symmetric removal process may be problematic because a substrate having an asymmetrically non-uniform thickness profile will, due to a uniform material removal rate across the substrate surface during polishing, remain asymmetric after the CMP process is complete and will require further polishing. Thus, CMP processes lack tunability on a device or feature level. In most cases, keeping over polish (OP) windows low is the known strategy for keeping device ranges low. However, low OP windows lead to unwanted residue, including polar or radial residue, across the wafer and subsequent reworking of the wafer through the polisher, resulting in a nonselective polishing process which polishes both the dies with unwanted residue as well as the dies without unwanted residue. [0004] For example, the asymmetric thickness of the substrate may result in the circuits formed in the substrate having a different RC time constant for the integrated circuits in devices, or dies, formed on opposing sides or edges of the same surface of the substrate, due to the ICs formed on the thinner edge of the substrate having less metal than the ICs formed on the thicker edge of the substrate. The resulting integrated circuits will have processing speeds that vary based on the corresponding substrate thickness. Thus, the variance in RC time constants results in devices of varying performance and quality, which is not desirable. Although described as on opposing sides or edges, the location of the thinnest and thickest sides or areas of the substrate may be in other non-symmetric locations of the substrate. [0005] Accordingly, there is a need in the art for an apparatus and methods of correcting asymmetry in topology of the surface of a substrate during a CMP process. SUMMARY [0006] Embodiments of the disclosure provide a method of removing material from a substrate, comprising urging a device surface of a substrate against a polishing surface of a polishing pad disposed on a surface of a platen, wherein the polishing pad comprises a second surface that is positioned opposite to the polishing surface in a first direction, and a plurality of cavities formed in the second surface, and the platen comprises one or more ports, and each port of the one or more ports is in fluid communication with a cavity of the plurality of cavities. The method of removing material also includes translating the substrate relative the polishing surface of the polishing pad, and applying a positive pressure or a negative pressure to a cavity of the plurality of cavities through the port that is in fluid communication with the cavity, wherein applying the positive pressure or the negative pressure to the cavity causes a first portion of the polishing surface of the polishing pad to alter its position relative to a second portion of the polishing surface when measured in the first direction. [0007] Embodiments of the disclosure may further provide a method of removing material from a substrate. The method of removing material also includes urging a device surface of a substrate against a polishing surface of a polishing pad disposed on a surface of a platen, where the polishing pad may include: a second surface that is positioned opposite to the polishing surface in a first direction, and a plurality of cavities formed in the second surface. The platen may include one or more ports, and each port of the one or more ports is in fluid communication with a cavity of the plurality of cavities. The method of removing material also includes translating the substrate relative the polishing surface of the polishing pad while applying a first positive pressure or a first negative pressure to a first cavity of the plurality of cavities through the port that is in fluid communication with the cavity, where applying the first positive pressure or the first negative pressure to the first cavity causes a first portion of the polishing surface of the polishing pad to alter its position relative to a second portion of the polishing surface when measured in the first direction; and translating the substrate relative the polishing surface of the polishing pad while applying a second positive pressure or a second negative pressure to a second cavity of the plurality of cavities through the port that is in fluid communication with the cavity, where applying the second positive pressure or the second negative pressure to the cavity causes a third portion of the polishing surface of the polishing pad to alter its position relative to the second portion of the polishing surface when measured in the first direction. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods. [0008] Embodiments of the disclosure may further provide a chemical mechanical polishing (CMP) system that includes a polishing pad that includes a polishing surface, a second surface that is positioned opposite to the polishing surface in a first direction, and a plurality of cavities formed in the second surface. The polishing pad may also include an adhesion layer. The CMP system will include a platen that includes a body that includes a pad supporting surface, and one or more ports formed in the body that are configured to receive a positive or a negative pressure that is generated from a fluid control device. Each cavity of the plurality of cavities of the polishing pad is in fluid communication with at least one of the one or more ports, and the adhesion layer, if present, is disposed between the pad supporting surface of the platen and a portion of the second surface of the polishing pad. [0009] Embodiments of the disclosure may further provide a chemical mechanical polishing (CMP) polishing pad that includes a polishing surface, a second surface that is positioned opposite to the polishing surface in a first direction, and a plurality of cavities formed in the second surface. The polishing pad may also include an adhesion layer. Each cavity of the plurality of cavities of the polishing pad are configured to be in fluid communication with at least one port of a plurality of ports formed in a pad supporting surface of platen on which the polishing pad is disposed, and the adhesion layer, if present, is disposed between the pad supporting surface of the platen and a portion of the second surface of the polishing pad. BRIEF DESCRIPTION OF THE DRAWINGS [0010] So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only exemplary embodiments and are therefore not to be considered limiting of its scope, and may admit to other equally effective embodiments. [0011] FIG.1 depicts a schematic top view of an exemplary chemical mechanical polishing system according to embodiments described herein. [0012] FIG.2 depicts a schematic sectional view of an exemplary polishing station of the chemical mechanical polishing system from FIG.1 according to embodiments described herein. [0013] FIG.3A-3B depict schematic side views of an exemplary polishing pad and platen of the chemical mechanical polishing system from FIG. 1 according to embodiments described herein. [0014] FIG.4A-4B depict schematic top views of an exemplary platen assembly of the chemical mechanical polishing system from FIG. 1 according to embodiments described herein. [0015] FIG. 5 depicts a method of selectively polishing a substrate according to embodiments described herein. [0016] FIG.6 is a functional block diagram illustrating components of a controller according to embodiments described herein. [0017] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation. DETAILED DESCRIPTION [0018] In the following description, details are set forth by way of example to facilitate an understanding of the disclosed subject matter. It should be apparent to a person of ordinary skill in the field, however, that the disclosed implementations are exemplary and not exhaustive of all possible implementations. Thus, it should be understood that reference to the described examples is not intended to limit the scope of the disclosure. Any alterations and further modifications to the described devices, instruments, methods, and any further application of the principles of the present disclosure are fully contemplated as would normally occur to one skilled in the art to which the disclosure relates. In particular, it is fully contemplated that the features, components, and/or steps described with respect to one implementation may be combined with the features, components, and/or steps described with respect to other implementations of the present disclosure. As used herein, the term “about” may refer to a +/-10% variation from the nominal value. It is to be understood that such a variation can be included in any value provided herein. [0019] Aspects of the present disclosure provide apparatus and methods for correcting asymmetry in a thickness profile by use of a chemical mechanical polishing (CMP) process. [0020] Utilizing embodiments described herein, overpolishing of uneven substrate surfaces following a CMP process can be avoided. Embodiments described herein allow for selective reworking of a substrate following an initial CMP process by limiting the area and number of dies on an at least partially polished substrate which are exposed to a further CMP process. In this manner, selective polishing can be achieved. [0021] In certain polishing systems, a platen and a carrier head are used and a polishing pad is disposed on and affixed to the platen. A substrate to be polished is placed between the carrier head and the polishing pad. The carrier head and/or the platen and the polishing pad rotate as a slurry containing abrasive particles is applied to the surface of the polishing pad. A membrane in the carrier head is used to apply pressure on the substrate during polishing to adjust the material removal rate and control the planarization and uniformity results achieved on the substrate. However, prior to being polished, the substrate may have an initial asymmetrical, non-uniform thickness profile which, by use of conventional CMP processes, typically results in the asymmetric thickness profile being unchanged during and after polishing due to the symmetric material removal rate provided in the conventional CMP process. As discussed further below, in order to counteract the initial asymmetric thickness profile, a selective removal profile is created by use of one or more of the embodiments described herein. The selective removal profile, when known, combined with the substrate’s initial asymmetric thickness profile can result in a polished substrate having a final thickness profile that is highly uniform and symmetric. [0022] The substrate’s initial thickness profile and the location or locations of remaining residue may be determined using different measurement or metrology tools and methods including, but not limited to, interferometry or full wafer imaging. In certain embodiments, a metrology station may be used to measure the thickness profile and/or locate indices of residue locations on the wafer. The thickness profile may be referenced to a feature or marking on the substrate through a reference mapping of the surface of the substrate. For example, the substrate may include a V- shaped notch in its perimeter or edge and the orientation of the thickness profile is noted or logged in reference to the notch. As is discussed further below, the reference mapping is used when developing the selective removal profile. [0023] In some embodiments, a selective removal profile may be achieved by varying a contact surface of the polishing pad with a device side of the substrate. As is discussed further below, by varying the contact surface of the polishing pad with the device side of the substrate, the polishing process can be selective at a die or feature level, such that additional polishing is focused on and/or limited to dies with remaining residue. In this manner, a selective removal profile can be created which can identify one or more discrete regions by which an upper surface of the polishing pad is in contact with the device side of a substrate. The selective removal profile may be achieved via an algorithm driven die tracker which receives the indices of residue locations on the surface of the substrate and identifies the discrete regions of the polishing pad, for a given relative motion between the substrate and platen and rotational speed of the substrate disposed in the carrier head and/or platen, that the residue locations will pass through as a function of time. The algorithm driven die tracker can thus create a discrete path across the surface of the polishing pad during a polishing process. In some embodiments, the indices of residue locations are input manually into a computer which, in turn, outputs a discrete polishing path. In other embodiments, the indices of residue locations are automatically sent to a computer which, in turn, outputs a discrete polishing path. [0024] This application often refers to a rotation, rotational rate, rotational speed, speed, and/or velocity in relation to the motion of the carrier head 210 (FIG. 2). However, it should be understood that such discussion also will similarly apply to the substrate 115, unless otherwise noted, because the substrate 115 is in contact with and rotates with the carrier head 210. While the present application refers to rotational speeds, rotational rates, speeds, and velocities, these terms are not meant to be limiting and may be used interchangeably unless specifically noted. For example, velocity may mean a velocity with a speed and a direction or a magnitude of a velocity (e.g., speed). [0025] FIG. 1 is a top plan view illustrating one embodiment of a chemical mechanical polishing (CMP) system 100. The CMP system 100 includes a factory interface module 102, a cleaner 104, and a polishing module 106. A wet robot 108 is provided to transfer substrates 115 between the factory interface module 102 and the polishing module 106. The wet robot 108 may also be configured to transfer the substrates 115 between the polishing module 106 and the cleaner 104. The factory interface module 102 includes a dry robot 110 which is configured to transfer the substrates 115 between one or more cassettes 114, one or more metrology stations 117, and one or more transfer platforms 116. In some embodiments, as shown in FIG.1, four substrate storage cassettes 114 are shown. The dry robot 110 within the factory interface 102 has sufficient range of motion to facilitate transfer between the four cassettes 114 and the one or more transfer platforms 116. Optionally, the dry robot 110 may be mounted on a rail or track 112 to position the robot 110 laterally within the factory interface module 102. The dry robot 110 is also configured to receive the substrates 115 from the cleaner 104 and return the clean polished substrates to the substrate storage cassettes 114. [0026] Still referring to FIG. 1, the polishing module 106 includes a plurality of polishing stations 124 on which the substrates 115 are polished while being retained in a carrier head 210. The polishing stations 124 are sized to interface with one or more carrier heads 210 so that polishing of a substrate 115 may occur in a single polishing station 124. The carrier heads 210 are coupled to a carriage (not shown) that is mounted to an overhead track 128 that is shown in phantom in FIG. 1. The overhead track 128 allows the carriage to be selectively positioned around the polishing module 106 which facilitates positioning of the carrier heads 210 selectively over the polishing stations 124 and load cup 122. In some embodiments, as shown in FIG. 1, the overhead track 128 has a circular configuration which allows the carriages retaining the carrier heads 210 to be selectively and independently rotated over and/or clear of the load cups 122 and the polishing stations 124. [0027] In some embodiments, as shown in FIG.1, three polishing stations 124 are shown located in the polishing module 106. At least one load cup 122 is in the corner of the polishing module 106 between the polishing stations 124 closest to the wet robot 108. The load cup 122 facilitates transfer between the wet robot 108 and the carrier heads 210. [0028] Each polishing station 124 includes a polishing pad 204 having a polishing surface (e.g., a polishing surface 204A in FIG.2) capable of polishing a substrate 115. Each polishing station 124 includes one or more carrier heads 210, a conditioning assembly 132 and a polishing fluid delivery module 135. In some embodiments, the conditioning assembly 132 may comprise a pad conditioning assembly 140 which dresses the polishing surface of the polishing pad 204 by removing polishing debris and opening the pores of the polishing pad 204 by use of a pad condition disk 133. In other embodiments, the polishing fluid delivery module 135 may comprise a fluid delivery arm 134 to deliver a slurry. Each polishing station 124 comprises a pad conditioning assembly 132. In some embodiments, the fluid delivery arm 134 is configured to deliver a fluid stream (e.g., a fluid 222 in FIG.2) to a polishing station 124. The polishing pad 204 is supported on a platen (e.g., a platen 202 in FIG. 2) which rotates the polishing surface during processing. The platen 202 includes a body 203 that has a pad supporting surface 327. The CMP system 100 is coupled with a power source 180. [0029] In some embodiments, the substrates 115, such as silicon wafers with one or more layers deposited thereon, are loaded into the CMP system 100 via a cassette 114. The substrate 115 will typically have a notch, flat or other type of reference mark that can be used to note a rotational orientation of a major surface of the substrate relative to a central axis. The factory interface module 102 extracts the substrate 115 from the cassette 114 to begin processing while a controller 190 coordinates operations of the CMP system 100. The factory interface module 102 transfers the substrate 115 to the metrology station 117, which measures a thickness profile of the substrate 115 as well as locates indices of residue locations on the surface of the substrate 115. The metrology station 117 may use interferometry, full wafer imaging, or other useful process as described in relation to FIG.2. The controller 190 receives the measurements and the orientation of the thickness profile from the metrology station 117 and tracks the orientation of the thickness profile using one or more fiducial marks or a notch as the substrate 115 is processed. The factory interface module 102 transfers the substrate 115 to the transfer platforms 116, and the wet robot 108 transfers the substrates through subsequent processing components including the CMP system 100. In some embodiments, the metrology station 117 is part of the factory interface module 102. In other embodiments, the metrology station 117 is housed in a separate module (not shown) connected to the factory interface module 102. [0030] The load cups 122 serve multiple functions, including receiving the substrate 115 from the wet robot 108, washing the substrate 115 and loading the substrate 115 into the carrier heads (e.g., a carrier head 210 in FIG.2). Each polishing station includes a polishing pad 204 secured to a rotatable platen 202. Different polishing pads 204 may be used at different polishing stations 124 to control the material removal of the substrate 115. Aspects of the CMP system operation are further described in FIG.2. [0031] In some embodiments, the factory interface module 102 can also include a pre-aligner 118 to position the substrate 115 in a known and desirable rotational orientation. The pre-alignment of the substrate to a desired rotational orientation allows the substrate to be positioned and oriented so that when the substrate is transferred by one or more robots in the system to a position where a carrier head 210 can receive the substrate, the substrate is oriented in a known and desirable orientation relative to the carrier heads 210 and rotatable platen 202. The pre-aligner 118 includes a notch detection system, such as an optical interrupter sensor (not shown), to sense when the substrate notch is at a specific angular position. Substrates 115 which might be in an uncertain angular position, e.g., after a polishing operation, have a known orientation when scanned by the metrology station 117, thus permitting accurate determination of the x-y (or r-^) position of the measurements on the substrate 115. [0032] In some embodiments, the substrates 115 are moved by the dry robot 110 to the metrology station 117 where properties of the substrate 115 are measured, as described herein. For example, the factory dry robot 110 “picks” up the substrate, e.g., by vacuum suction, and transports the unpolished substrate to the metrology station 117. The metrology station 117 may perform a plurality of thickness or residue location measurements across the substrate 115. The controller 190 may determine the discrete polishing path from the thickness and/or residue locations of the substrate 115. [0033] The dry robot 110 then transfers each substrate 115 to a transfer platform 116, and then the wet robot 108 transports the substrate to the different polishing stations 124 within the CMP system 100. Eventually the substrate 115 is loaded into a load cup 122 so that a carrier head 210 can retain and transport the substrate 115 to each of the one or more polishing stations 124 to undergo a CMP process according to the polishing parameters selected. During CMP, the controller 190 controls aspects of the polishing stations 124. In some embodiments, the controller 190 is one or more programmable digital computers executing digital control software. The controller 190 can include a processor 192 situated near the polishing apparatus, e.g., a programmable computer, such as a personal computer. The controller can include a memory 194 and support circuits 196. The controller 190 can, for example, coordinate contact between the substrate 115 and the polishing pad 204 at differing rotational speeds such that a selective removal profile is aligned with indices of residue locations on the substrate 115, such as an asymmetric thickness profile of the substrate 115. Aligning these profiles ensures the thickest part of the substrate 115 has the most material removed and reduces the asymmetry of the substrate 115 during polishing. The controller 190 is further described in FIG.6. The controller 190 may be a plurality of controllers 190. In some embodiments, the controller 190 includes a liquid dispenser module (LDM) for controlling the FCVs 404 and a fluid control device 402, such as a pump 402. [0034] After polishing, the wet robot 108 transports the substrate 115 from the load cup 122 to a cleaning chamber in the cleaner 104, where slurry and other contaminants that have accumulated on the substrate surface during polishing are removed. In the embodiment depicted in FIG.1, the cleaner 104 includes two pre- clean modules 144, two megasonic cleaner modules 146, two brush box modules 148, a spray jet module 150, and two dryers 152. [0035] The dry robot 110 then removes the substrate 115 from the cleaner 104 and transfers the substrate 115 to the metrology station 117 to be measured again. In certain embodiments, the post-polish layer measurements can be used to adjust the polishing process parameters for a subsequent substrate. Finally, the dry robot 110 returns the substrate 115 to one of the cassettes 114. [0036] FIG.2 depicts a schematic sectional view of a polishing station 124 of the CMP system 100 from FIG. 1 that comprises a polishing assembly 200 having a polishing pad 204 formed according to embodiments described herein. In particular, FIG.2 shows how a carrier head 210 is positioned relative to the polishing pad 204. A coordinate system 201, having an x-axis, a y-axis, and a z-axis, shows the orientation of the different components of the polishing assembly 200 in this and subsequent figures. The coordinate system 201 shows positive directions of the x, y, and z-axes and positive direction for rotation about the z-axis, which is in a counter- clockwise direction. The opposite directions (not shown) are negative directions. [0037] In some embodiments, the polishing pad 204 is secured to the pad supporting surface 327 of a platen 202 using an adhesive layer 220, such as a pressure sensitive adhesive (PSA) layer, as shown in FIG.3, disposed between the polishing pad 204 and the pad supporting surface 327 of the platen 202. In some embodiments, the PSA layer can include a rubber resin, acrylic or silicone containing material. The carrier head 210, facing the platen 202 and the polishing pad 204 mounted thereon, includes a flexible diaphragm 212 configured to impose different pressures in different regions of the flexible diaphragm 212 against a surface of a substrate 115 that is disposed between the carrier head 210 and the polishing pad 204. The carrier head 210 includes a carrier ring 218 surrounding the substrate 115 which holds the substrate in place. The carrier head 210 rotates about a carrier head axis 216 while the flexible diaphragm 212 urges a to-be-polished surface of the substrate 115, such as a device side of the substrate 115, against a polishing surface 204A of the polishing pad 204. During polishing, a downforce on the carrier ring 218 urges the carrier ring 218 against the polishing pad 204 to improve the polishing process uniformity and prevent the substrate 115 from slipping out from under the carrier head 210. In some embodiments, the carrier head 210 includes a shaft 211 which has an axis that is collinear with carrier head axis 216. In some embodiments, the platen 202 and the carrier head 210 each have a rotation sensor (not shown), such as an encoder, to measure their angular position and/or rotation rate as they rotate and a mechanism or motor (not shown) driving their rotation. [0038] In some embodiments, the polishing pad 204 rotates about a platen axis 205. The polishing pad 204 has a polishing pad axis 206 that is collinear with the platen axis 205. In some embodiments, the polishing pad 204 rotates in the same rotational direction as the rotation direction of the carrier head 210. For example, the polishing pad 204 and carrier head 210 both rotate in a counter-clockwise direction. As shown in FIG.2, the polishing pad 204 has a surface area that is greater than the to-be-polished surface area of the substrate 115. However, in some embodiments, the polishing pad 204 has a surface area that is less than the to-be-polished surface area of the substrate 115. [0039] In some embodiments, an endpoint detection (EPD) system 224 detects reflected light that is directed towards the substrate 115 from a light source, through a platen opening 226 and an optically transparent window feature 227 of the polishing pad 204 disposed over the platen opening 226, and then back through these components to a detector (not shown) within the EPD system 224 during processing to detect properties of a layer formed on a surface of the substrate during polishing. The EPD system 224 can allow a thickness and/or residue location measurement, of the substrate 115 to be taken while the polishing assembly 200 is in use if the angular and radial position of the EPD system 224 within the platen 202 are known relative to the angular and lateral position of notch of substrate 115. In some embodiments, an eddy current probe is used to measure the thickness of conductive layers formed on a region of a surface of the substrate 115 by the comparison of the relative angle and position of the notch of the substrate 115, or carrier head 210, to the EPD system 224 within the platen 202. [0040] Notably, this application may refer to a rotation, rotation rate, speed, and/or velocity of the carrier head 210. It should be understood that such discussion also applies to the substrate 115, unless otherwise noted, because the substrate 115 generally rotates with the carrier head 210. [0041] During polishing, the fluid 222 is introduced to the polishing pad 204 through the fluid delivery arm 134 portion of the polishing fluid delivery module 135, which is positioned over the polishing pad 204. In some embodiments, the fluid 222 is a polishing fluid, a polishing slurry, a cleaning fluid, or a combination thereof. In some embodiments, the polishing fluid may include water based chemistries that include abrasive particles. The fluid 222 may also include a pH adjuster and/or chemically active components, such as an oxidizing agent, to enable CMP of the material surface of the substrate 115 in conjunction with the polishing pad 204. The fluid 222 removes material from the substrate as the carrier head 210 urges the substrate against the polishing pad 204. [0042] FIG.3A is a side view of the polishing pad 204 and the platen 202 of the CMP system according to some embodiments. In some embodiments, as shown in FIG.3A, the polishing pad 204 includes a foundation layer 307 and a polishing layer 308. The polishing layer 308 includes polishing structures 309 that are formed on or bonded to the foundation layer 307, or are an inseparable part of the foundation layer 307. In some embodiments, the foundation layer 307 and the polishing layer 308 of the polishing pad 204 are formed layer-by-layer using a 3D printing process. In some embodiments, the polishing layer 308 includes a material that has different mechanical and/or chemical properties from the material in the foundation layer 307. In one example, the polishing layer 308 includes a polymeric material that has hardness that is greater than the material found in the foundation layer 307. [0043] In some embodiments, the polishing pad 204 is secured to the platen 202 via the adhesive layer 220. The adhesive layer 220 may be a PSA layer. In some embodiments, the adhesive layer 220 is disposed between the foundation layer 307 and the platen 202. The platen 202 further includes a plurality of ports 323 formed therethrough (further described with regard to FIG.4A below), and thus extend from the pad supporting surface 327 of the platen to a second surface 328 of the platen 202, which is opposite to the pad supporting surface 327. The plurality of ports 323 each have a first end 331 proximate the foundation layer 307 of the polishing pad 204 and a second end 333 distal to the polishing pad 204. A plurality of cavities 325 are formed between the platen 202 and the polishing pad 204 at the first end 331 of each of the plurality of ports 323 such that each of the plurality of ports 323 is fluidly coupled to a respective cavity 325 of the plurality of cavities 325. The cavities 325 are generally defined by a lower portion of the polishing pad 204, such as a lower surface 307A of a portion of the foundation layer 307, and a portion of the pad supporting surface 327 of the platen 202. In some examples, one or more of the cavities 325 is substantially hemisphere shaped or curved relative to a vertical plane (e.g., X-Z plane in FIG. 3A). In other embodiments, one or more of the cavities 325 are concentric radial grooves that are centered about the central axis of the platen 204. In other embodiments, one or more of the cavities 325 are formed in radially positioned sectors (e.g., portion of a disk that is defined by two radii separated by an arc angle, an inner radius and an outer radius), when viewed in the –Z-direction, that are centered about the central axis of the platen 204. In other embodiments, one or more of the cavities 325 is substantially dome shaped with vertically linear walls, as shown in FIG.3A. In this configuration, the pump 402 may include a first device (e.g., vacuum pump) that is configured to generate a vacuum that can be applied to a first portion of the plurality of cavities 325 and/or a second device (e.g., mechanical pump or gas source (e.g., air, N ₂ , He source)) that is configured to generate and apply a positive pressure to a second portion of the plurality of cavities 325. In many of the embodiments described herein, the cavities 325 can be generally described as being similar to a blind hole or blind channel region, and thus a fluid (e.g., gas or liquid) disposed within an open area defined by the surfaces that define each cavity 325 can only enter and exit this enclosed region through a ports 323 that is in fluid communication with the open area of the cavity 325. [0044] In some configurations, a multiple port rotary feedthrough 251 may be coupled between each of the FCVs 404 and each of the plurality of ports 323 to allow the pump 402 to fluidly communicate with the cavities 325 disposed on and the ports 323 formed in a rotating platen 202. In some embodiments, the rotary feedthrough 251 is a Ferro-fluidic type of feedthrough. In other embodiments, the rotary feedthrough 251 is a rotary feedthrough that includes a plurality of sealing members (e.g., O-rings). [0045] FIG.3B is a side view of the polishing pad 204 and the platen 202 of the CMP system according to some embodiments. As shown in FIG. 3B, retracted regions 310 of the polishing pad 204 are retracted such that at least portions of the polishing surface 204A of the polishing pad 204 are retracted relative to un-retracted regions 312 of the polishing surface 204A so that the retracted regions 310 are no longer in contact with the surface of the substrate 115 to be polished and a retraction gap 330 is created between the retracted portions of the polishing pad 204 and the surface of the substrate 115 that is in contact with the un-retracted region 312. Retracted regions 310 of the polishing pad 204 may be retracted by the pump 402 configured to generate a vacuum to a first portion of the plurality of cavities 325. In one example, a retraction gap from about 50 micrometers (μm) to about 200 μm, or even from about 50 μm to about 75 μm, can be used to avoid unwanted polishing contact between the retracted regions 310 of the polishing pad 204 the surface of the substrate 115 to be polished. [0046] Through the use of the plurality of ports 323, it is possible to retract regions 310 of the polishing surface 204A of the polishing pad 204 and prevent these area from making contact with the surface of the substrate 115 to be polished at specific times during a polishing process, such as a CMP process. In other words, by timing the evacuation of the each cavity 325, by use of signals from the controller 190 to control the opening and closing of the FCVs 404, relative to the position of residue locations on the surface of the substrate at any instant in time, residue location regions on the substrate surface can include higher material removal rates versus non-residue containing regions based on the non-evacuation of one or more cavities 325 versus evacuation of other one or more cavities 325, respectively. Further, by preventing contact with the surface of the substrate 115 to be polished, embodiments described herein allow for the creation and implementation of a selective removal profile whereby only desired areas of the substrate 115 are polished, such as one or more residue locations. This selective removal profile, in turn, allows for a higher overall throughput and polishing efficiency. [0047] FIG.4A is a top plan view of the platen 202 of the CMP system according to some embodiments. In some embodiments, the plurality of ports 323 are arranged in circular arrays that are positioned in concentric rings disposed relative to a center axis 205 of the platen 202. Each of the plurality of ports 323 may be equally spaced on the concentric rings. In some embodiments, as shown in FIG.4A, the plurality of ports 323 are arranged concentric channels 403 that are aligned radially relative to the center axis 205 of the platen 202. In this configuration, each of the plurality of ports 323 may be equally spaced on the concentric channels 403. For example, as shown in FIG.4A, three concentric channels of eight equally spaced (along the rings) ports 323 may be present. It is contemplated that less than 25 ports 323 may be present, such as 24 or less, or even between 15 to 25 ports. In some embodiment, more than 25 ports 323 may be present, such as greater than 50 ports 323. It is further contemplated that two or more concentric rings may be utilized, such as three or more rings, four or more rings, five or more rings, or even six or more rings. Alternative patterns of ports 323 are also considered such as non-radial or concentric grid patterns, sector pattern, rectangular pattern or patterns that is align with pad groove direction (e.g., aligned to a spiral groove pattern formed in the polishing pad). In some embodiments, the ports 323 are disposed in a radial pattern that extends from the central axis 205 of the platen 202. In some embodiments, each of the plurality of ports 323 is separately fluidly coupled to a flow control valve (FCV) 404 (FIG. 3A). In some embodiments, each of the flow control valves (FCV) 404 are coupled to a pressure regulating device (not shown) that is configured to adjust the pressure level in a cavity 325 when the flow control valve is opened during processing. In some embodiments, groups of two or more of the ports 323 are fluidly coupled to a flow control valve (FCV) 404. In some embodiments, all of the FCVs are coupled to a single pump 402 (FIG.3A). In some embodiments, each of the plurality of ports 323 is fluidly coupled to a respective FCV 404 of a plurality of FCVs 404 and a respective pump 402 of a plurality of pumps 402. [0048] In some embodiments, the pump 402 is a vacuum pump configured to create a vacuum within each selected port 323 of plurality of ports 323 such that each of the respective cavities 325 at least partially collapse when a vacuum pressure is applied to cavities 325 by the pump 402 and corresponding areas (i.e., retracted regions 310) of the polishing pad 202 are retracted away from a surface of the substrate 115 that is disposed on the un-retracted regions 312 of the polishing pad 202. For example, as shown in FIG. 4B, retracted regions 310 (i.e., illustrated as dashed regions) of the polishing pad 204 are retracted such that at least portions 204C of the polishing surface 204A of the polishing pad 204 are retracted relative to other portion 204B of the polishing surface 204A so that these portions 204C are no longer in contact with a portion 115A of the surface of the substrate 115 to be polished. Each of the retracted regions 310 may correspond to a residue area 115A that does not need to be polished at as high of a rate as a portion 115B on the surface of the substrate 115 that are in contact with the un-retracted regions 312. It is also contemplated that cavities 325 that are directly beneath the high residue areas will be filled with a higher than atmospheric pressure gas than cavities 325 in surrounding areas of the polishing pad 202 in order to increase the hardness of the polishing pad and thus alter the polishing characteristics of the polishing pad 202, such as increase the polishing rate. [0049] During operation, as the polishing pad rotates and the substrate is urged against the surface of the polishing pad 202 by the carrier head 210, a discrete path 425 across the surface of the polishing pad is developed and implemented during a polishing process by use of the controller 190. For example, discrete polishing path 425 in FIG. 4B, which is a portion of the orbital path that a portion of a substrate traverses during a portion of a polishing process. The discrete polishing path 425 is formed due at least in part to the polishing pad 204 and the carrier head 210 rotating in a clockwise or counterclockwise direction about their respective central axes. Typically, as the polishing pad 204 and the carrier head 210 are rotated during a CMP process, the carrier head 210 is also translated in an arc or radial motion with respect to the platen 202. The discrete path 425 is thus formed by a combination of the translation of the carrier head 210 with respect to the platen 202 as well as the rotation of the polishing pad 204 and the carrier head 210, which is monitored by the controller so that the formation of retracted regions 310 and un-retracted regions 312 can be generated at desired instants in time to specifically alter the polishing profile of different regions of the surface of the substrate. [0050] FIG. 5 is a method 500 of selectively polishing a substrate according to some embodiments that can be performed in a polishing system such as the CMP system 100 illustrated in FIG.1. While the process sequence described in relation to FIG. 5 primarily focuses on the operations used to perform a selective polishing process, this shortened list of operations is not intended to be limiting as to the scope of the disclosure described herein since other polishing process operations may be inserted before, during, or after the operations discussed in relation to the selective polishing process without deviating from the basic scope of the disclosure provided herein. For example, one or more cleaning operations may be performed on a substrate in the cleaner 104 within the CMP system 100 before or after the method 500 of selectively polishing has been performed on a substrate. [0051] At operation 502, a substrate, such as the substrate 115, is first taken out of a cassette, such as cassette 114, then the orientation of the substrate 115 is determined by an aligner, such as the aligner 118. The substrate 115 is then transferred to the metrology tool, such as the metrology station 117, for processing. In some embodiments, at the start of method 500 the surface of the substrate 115 is an unpolished surface. [0052] At operation 504, a metrology tool, such as the metrology station 117, locates one or more areas of residue on the surface of the substrate 115. The areas of residue include areas that have a differing thickness relative to the mean thickness of the substrate, such as relative “high points” or “high regions” on the surface of the substrate. In some embodiments, locating the one or more areas of residue may involve an integrated camera or other imager in order to obtain die level topography, thickness information or other optical property information such as opacity. In some embodiments, interferometry may be utilized to locate the one or more areas of residue which require further polishing. The metrology tool may be in-situ or ex-situ relative to the polishing system 100. [0053] At operation 506, a controller, such as the controller 190, receives information regarding the one or more areas of residue, which is also referred to herein as the “indices” of residue locations on the at least partially polished substrate 115 as well as the rotational speed of the polishing pad 204 from a first sensor 260 coupled to the platen 202 and/or a second sensor 270 coupled to the carrier head 210 and outputs a selective removal profile for the substrate 115. The selective removal profile may be an identified polishing path based upon known process conditions, such as rotational and translation speed of the carrier head 210 and/or the polishing pad 204 disposed on the platen 202. In some embodiments, the indices of residue locations and the rotational speed information are provided manually to the controller 190 by a user. In other embodiments, the indices of residue locations and the rotational speed information are provided automatically to the controller 190 by the various sensors and/or by use of local controllers that are coupled to the controller 190 via a communication network. [0054] At operation 507, a surface of a substrate to be polished, such as the substrate 115, is urged against a polishing pad 204 by a carrier head, such as the carrier head 210 in a CMP process. Prior to operation 507, the substrate 115 is placed in a desired orientation within the carrier head 210 by use of a robot based on the alignment determined during operation 504. In some embodiments, the controller 190 determines a desired alignment of the substrate 115 in the carrier head 210, such that a desired polishing path for one or more residue regions on the surface of the substrate can controlled. The controller 190 can coordinate the movement of the one or more residue regions on the surface of the substrate 115 across regions of the polishing pad by controlling the rotation and/or translation of the carrier head 210 and/or rotation speed of the platen 202.

[0055] At operation 508, by use of the controller 190, a pump, such as the pump 402, and selected valves, such as selected FCVs 402 of the plurality of FCVs 402, create a vacuum in the respective ports 323 so that a portion or portions of the polishing pad 204 are retracted and do not make contact with the non-residue containing regions of the surface of the substrate 115 during a current portion of the CMP process. It is also contemplated that rather than retract portions of the polishing pad 204, portions of the polishing pad 204 may be expanded by filling selected cavities 325 with pressurized fluid such that only the pressurized portions of the polishing pad make contact with the residue containing regions (e.g., high points) formed on the surface of the substrate 115 during a current portion of the CMP process. It is also contemplated that the selective removal profile from portions of the surface of the substrate identified during operations 504-506 can be adjusted in real-time during a polishing process through control of the pump 402 and selected FCVs 402 by the execution of one or more software programs stored within the memory of the controller 190. In some embodiments, the controller 190 is configured to adjust the application of a positive pressure or a negative pressure to a cavity 325 as the substrate is translated relative to the polishing surface of the polishing pad 204, wherein the application of the positive pressure or negative pressure to the cavity 325 is based on the position of one or more residue locations to the cavity 325. The process of adjusting the application of a positive pressure or a negative pressure to a cavity 325 may include adjusting the positive or the negative pressure level in the cavity 325 between two or more instants in time. The process of adjusting the application of a positive pressure or a negative pressure to a cavity 325 may also include applying a negative pressure at a first instant in time and then not applying a negative pressure (e.g., venting the cavity to atmospheric pressure) at a second instant in time, applying a positive pressure at a first instant in time and then not applying a positive pressure (e.g., venting the cavity to atmospheric pressure) at a second instant in time, or even applying a negative pressure or a positive pressure at a first instant in time and then applying a positive pressure or a negative pressure at a second instant in time, respectively.

[0056] At operation 510, the surface of the at least partially polished substrate 115 is urged against the un-retracted regions 312 of the polishing pad 204 by the components within the carrier head 210, such that only a selected portion or portions of the polishing pad 204 contact the surface of the at least partially polished substrate 115. It is also considered that reduced, but not eliminated, contact may still be used to substantially lower material removal rates (e.g., a retraction gap from about 1 pm to about 50 pm) in certain regions of the substrate’s surface. Operations 506 through 510 may be optionally repeated in order to further polish dies not in a good planarization range (e.g., a range of about <100 A or less).

[0057] FIG. 6 depicts a functional block diagram of one example of a controller 190 for a carrier head (e.g., the carrier head 210 in FIG. 2) and/or a platen or a polishing pad (e.g., the platen 202 or the polishing pad 204 in FIG. 2). The controller 190 includes a processor 192 in data communication with a memory 194, an input device 630, and an output device 640. Though not shown, the controller 190 may include a distributed set of local controllers that are in communication with the controller 190.

The local controller can include similar components as shown and discussed in relation to controller 190 herein. In some embodiments, the processor 192 is further in data communication with an optional network interface card 650 that is used to communicate with the various sensors, automation components, robots and other useful devices. Although described separately, it is to be appreciated that functional blocks described with respect to the controller 190 need not be separate structural elements. For example, the processor 192 and memory 620 is embodied in a single chip. The processor 192 can be a general purpose processor, a digital signal processor (“DSP"), an application specific integrated circuit (“ASIC”), a field programmable gate array (“FPGA”) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any suitable combination thereof designed to perform the functions described herein. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0058] The processor 192 can be coupled, via one or more buses, to read information from or write information to memory 620. The processor may additionally, or in the alternative, contain memory, such as processor registers. The memory 620 can include processor cache, including a multi-level hierarchical cache in which different levels have different capacities and access speeds. The memory 620 can also include random access memory (RAM), other volatile storage devices, or nonvolatile storage devices. The storage can include hard drives, flash memory, etc. In various instances, the memory is referred to as a computer-readable storage medium. The computer-readable storage medium is a non-transitory device capable of storing information, and is distinguishable from computer-readable transmission media such as electronic transitory signals capable of carrying information from one location to another. Computer-readable medium as described herein may generally refer to a computer-readable storage medium or computer-readable transmission medium.

[0059] The processor 192 also may be coupled to an input device 630 and an output device 640 for, respectively, receiving input from and providing output to a user of the controller 190. Suitable input devices include, but are not limited to, a keyboard, buttons, keys, switches, a pointing device, a mouse, a joystick, a remote control, an infrared detector, a bar code reader, a scanner, a video camera (possibly coupled with video processing software to, e.g., detect hand gestures or facial gestures), a motion detector, or a microphone (possibly coupled to audio processing software to, e.g., detect voice commands). The input device 630 includes an encoder or other sensor to measure the rotation of the carrier head 210 or the platen 202 as discussed in FIG. 2. Suitable output devices include, but are not limited to, visual output devices, including displays and printers, audio output devices, including speakers, headphones earphones and alarms additive manufacturing machines and haptic output devices. As discussed in FIG. 2, the output device 640 includes various electrical components that are configured to drive and control a mechanism or motor that is used to drive the rotation of the carrier head 210 or the platen 202.

[0060] In certain embodiments, the processor 192 includes a timing element 615 such as a crystal or resistor-capacitor combination, and is used as part of an internal oscillator. The timing element may be used by the processor 192 to keep time and, for example, may be used with the encoder to calculate a rotation rate.

[0061] In further embodiments, the input device 630, the output device 640, the network interface card 650, and/or other components are considered support circuits (e.g., the support circuits in FIG. 1).

[0062] Utilizing embodiments described herein, overpolishing of uneven substrate surfaces following a CMP process can be avoided. As aforementioned, embodiments described herein allow for selective reworking of a substrate following an initial CMP process by limiting the area and number of dies on an at least partially polished substrate which are exposed to a further CMP process. In this manner, selective polishing can be achieved even down to 1 or 2 individual dies. Methods described herein allow for device level planarity by increasing die polishing control and selectivity.

[0063] The preceding description is provided to enable any person skilled in the art to practice the various embodiments described herein. The examples discussed herein are not limiting of the scope, applicability, or embodiments set forth in the claims. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments. For example, changes are made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as appropriate. For instance, the methods described may be performed in an order different from that described, and various steps may be added, omitted, or combined. Also, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented or a method may of the disdosure is intended to cover such an apparatus or method that is practiced using other structure, functionality, or structure and functionality in addition to, or other than, the various aspects of the disdosure set forth herein. It should be understood that any aspect of the disdosure disdosed herein may be embodied by one or more elements of a daim.

[0064] The methods disdosed herein comprise one or more steps or actions for achieving the methods. The method steps and/or actions may be interchanged with one another without departing from the scope of the daims. In other words, unless a specific order of steps or actions is spedfied, the order and/or use of spedfic steps and/or actions may be modified without departing from the scope of the daims. Further, the various operations of methods described above may be performed by any suitable means capable of performing the corresponding functions. The means may indude various hardware and/or software components) and/or module(s), including, but not limited to a circuit, an application spedfic integrated drcuit (ASIC), or processor. Generally, where there are operations illustrated in figures, those operations may have corresponding counterpart means-plus-function components with similar numbering.