Search NASA⌕ Search

SEARCH · Search NASA

Results for “lossless compression”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

Efficient transfer of images over networks

Effective remote observing requires sending large images over long distances. The usual approach to the transfer problem is to require high bandwidth transmission links, which are expensive to install and operate. An alternative approach is to use existing low-bandwidth connections, such as phone lines or the Internet, in a highly efficient manner by compressing the images. The combined use of existing low-cost infrastructure and standard networking software means that remote observing can be made practical even for small observatories with limited network resources. The authors have implemented such a scheme based on the H-transform compression method developed for astronomical images, which are often resistant to compression because they are noisy. The H-transform can be used for either lossy or lossless compression, and compression factors of at least 10 can be achieved with no noticeable losses in the astrometric or photometric properties of the compressed images. The H-transform allows us to organize the information in an image so that the 'useful' information can be sent first, followed by the noise, which makes up the bulk of the transmission. The receiver can invert a partially received set of H-coefficients, creating an image that improves with time. The H-transform is particularly well-suited to this style of incremental reconstruction, because the spatially localized nature of the basis functions of the H-transorm prevents the appearance of artifacts such as ringing around point sources and edges. The authors' implementation uses the WIYN Telescope Control System's TCP-based communications protocol. An 800x800 16-bit astronomical image was sent over a 2400 baud connection, which would normally take about 71 minutes; after only 60 seconds, the partially received H-transform produced an image that did not differ appreciably from the original. This poster presents a quantification of the efficiencies, as well as examples of images reconstructed from partial data.

Percival, J. W.↗

Portable and Transparent Message Compression in MPI Libraries to Improve the Performance and Scalability of Parallel Applications

The goal of this project has been to develop a lossless compression algorithm for message-passing libraries that can accelerate HPC systems by reducing the communication time. Because both compression and decompression have to be performed in software in real time, the algorithm has to be extremely fast while still delivering a good compression ratio. During the first half of this project, they designed a new compression algorithm called FPC for scientific double-precision data, made the source code available on the web, and published two papers describing its operation, the first in the proceedings of the Data Compression Conference and the second in the IEEE Transactions on Computers. At comparable average compression ratios, this algorithm compresses and decompresses 10 to 100 times faster than BZIP2, DFCM, FSD, GZIP, and PLMI on the three architectures tested. With prediction tables that fit into the CPU's L1 data acache, FPC delivers a guaranteed throughput of six gigabits per second on a 1.6 GHz Itanium 2 system. The C source code and documentation of FPC are posted on-line and have already been downloaded hundreds of times. To evaluate FPC, they gathered 13 real-world scientific datasets from around the globe, including satellite data, crash-simulation data, and messages from HPC systems. Based on the large number of requests they received, they also made these datasets available to the community (with permission of the original sources). While FPC represents a great step forward, it soon became clear that its throughput was too slow for the emerging 10 gigabits per second networks. Hence, no speedup can be gained by including this algorithm in an MPI library. They therefore changed the aim of the second half of the project. Instead of implementing FPC in an MPI library, they refocused their efforts to develop a parallel compression algorithm to further boost the throughput. After all, all modern high-end microprocessors contain multiple CPUs on a single die and will undoubtedly contain even larger numbers of CPUs in the future. Hence, a compute node in a parallel system is likely to have multiple processors per interconnection link. Thus, they investigated how to best exploit multiple CPUs to compress and decompress data for a single link, i.e., they developed a parallel version of the FPC algorithm called pFPC. On a 4-core 3 GHz Xeon system, pFPC exceeds 10 gigabits per second both in compression and decompression throughput while still reaching a compression ratio of 18%, which is reasonable for their double-precision floating-point datasets. At half this throughput, it achieves a 41% compression ratio. Moreover, the algorithm scales well to four cores and promises even higher throughputs on larger machines. Additional results and a description of the pFPC algorithm have recently been published in the proceedings of the Data Compression Conference. The C source code of pFPC is also publicly available.

97 MATHEMATICS AND COMPUTING↗

Improved Compression of Wavelet-Transformed Images

A recently developed data-compression method is an adaptive technique for coding quantized wavelet-transformed data, nominally as part of a complete image-data compressor. Unlike some other approaches, this method admits a simple implementation and does not rely on the use of large code tables. A common data compression approach, particularly for images, is to perform a wavelet transform on the input data, and then losslessly compress a quantized version of the wavelet-transformed data. Under this compression approach, it is common for the quantized data to include long sequences, or runs, of zeros. The new coding method uses prefixfree codes for the nonnegative integers as part of an adaptive algorithm for compressing the quantized wavelet-transformed data by run-length coding. In the form of run-length coding used here, the data sequence to be encoded is parsed into strings consisting of some number (possibly 0) of zeros, followed by a nonzero value. The nonzero value and the length of the run of zeros are encoded. For a data stream that contains a sufficiently high frequency of zeros, this method is known to be more effective than using a single variable length code to encode each symbol. The specific prefix-free codes used are from two classes of variable-length codes: a class known as Golomb codes, and a class known as exponential-Golomb codes. The codes within each class are indexed by a single integer parameter. The present method uses exponential-Golomb codes for the lengths of the runs of zeros, and Golomb codes for the nonzero values. The code parameters within each code class are determined adaptively on the fly as compression proceeds, on the basis of statistics from previously encoded values. In particular, a simple adaptive method has been devised to select the parameter identifying the particular exponential-Golomb code to use. The method tracks the average number of bits used to encode recent runlengths, and takes the difference between this average length and the code parameter. When this difference falls outside a fixed range, the code parameter is updated (increased or decreased). The Golomb code parameter is selected based on the average magnitude of recently encoded nonzero samples. The coding method requires no floating- point operations, and more readily adapts to local statistics than other methods. The method can also accommodate arbitrarily large input values and arbitrarily long runs of zeros. In practice, this means that changes in the dynamic range or size of the input data set would not require a change to the compressor. The algorithm has been tested in computational experiments on test images. A comparison with a previously developed algorithm that uses large code tables (generated via Huffman coding on training data) suggests that the data-compression effectiveness of the present algorithm is comparable to the best performance achievable by the previously developed algorithm.

Kiely, Aaron↗

Adaptive Vector-Quantization Scheme

Adaptive vector-quantization scheme provides for rapid encoding of signals for transmission in compressed form and for rapid decoding at receiver. Based on simple heuristic "move-to-front" protocol effecting lossless compression of high-rate textual data. Audio, video, or other signals compressed efficiently.

Cheung, Kar-Ming↗

Efficient DNA sequence compression with neural networks

Abstract Background The increasing production of genomic data has led to an intensified need for models that can cope efficiently with the lossless compression of DNA sequences. Important applications include long-term storage and compression-based data analysis. In the literature, only a few recent articles propose the use of neural networks for DNA sequence compression. However, they fall short when compared with specific DNA compression tools, such as GeCo2. This limitation is due to the absence of models specifically designed for DNA sequences. In this work, we combine the power of neural networks with specific DNA models. For this purpose, we created GeCo3, a new genomic sequence compressor that uses neural networks for mixing multiple context and substitution-tolerant context models. Findings We benchmark GeCo3 as a reference-free DNA compressor in 5 datasets, including a balanced and comprehensive dataset of DNA sequences, the Y-chromosome and human mitogenome, 2 compilations of archaeal and virus genomes, 4 whole genomes, and 2 collections of FASTQ data of a human virome and ancient DNA. GeCo3 achieves a solid improvement in compression over the previous version (GeCo2) of $2.4\%$, $7.1\%$, $6.1\%$, $5.8\%$, and $6.0\%$, respectively. To test its performance as a reference-based DNA compressor, we benchmark GeCo3 in 4 datasets constituted by the pairwise compression of the chromosomes of the genomes of several primates. GeCo3 improves the compression in $12.4\%$, $11.7\%$, $10.8\%$, and $10.1\%$ over the state of the art. The cost of this compression improvement is some additional computational time (1.7–3 times slower than GeCo2). The RAM use is constant, and the tool scales efficiently, independently of the sequence size. Overall, these values outperform the state of the art. Conclusions GeCo3 is a genomic sequence compressor with a neural network mixing approach that provides additional gains over top specific genomic compressors. The proposed mixing method is portable, requiring only the probabilities of the models as inputs, providing easy adaptation to other data compressors or compression-based data analysis tools. GeCo3 is released under GPLv3 and is available for free download at https://github.com/cobilab/geco3.

Silva, Milton↗

Black-box statistical prediction of lossy compression ratios for scientific data

Lossy compressors are increasingly adopted in scientific research, tackling volumes of data from experiments or parallel numerical simulations and facilitating data storage and movement. In contrast with the notion of entropy in lossless compression, no theoretical or data-based quantification of lossy compressibility exists for scientific data. Users rely on trial and error to assess lossy compression performance. As a strong data-driven effort toward quantifying lossy compressibility of scientific datasets, we provide a statistical framework to predict compression ratios of lossy compressors. Our method is a two-step framework where (i) compressor-agnostic predictors are computed and (ii) statistical prediction models relying on these predictors are trained on observed compression ratios. Proposed predictors exploit spatial correlations and notions of entropy and lossyness via the quantized entropy. We study 8+ compressors on 6 scientific datasets and achieve a median percentage prediction error less than 12%, which is substantially smaller than that of other methods while achieving at least a 8.8× speedup for searching for a specific compression ratio and 7.8× speedup for determining the best compressor out of a collection.

97 MATHEMATICS AND COMPUTING↗

On-the-Fly Decompression and Rendering of Multiresolution Terrain

We present a streaming geometry compression codec for multiresolution, uniformly-gridded, triangular terrain patches that supports very fast decompression. Our method is based on linear prediction and residual coding for lossless compression of the full-resolution data. As simplified patches on coarser levels in the hierarchy already incur some data loss, we optionally allow further quantization for more lossy compression. The quantization levels are adaptive on a per-patch basis, while still permitting seamless, adaptive tessellations of the terrain. Our geometry compression on such a hierarchy achieves compression ratios of 3:1 to 12:1. Our scheme is not only suitable for fast decompression on the CPU, but also for parallel decoding on the GPU with peak throughput over 2 billion triangles per second. Each terrain patch is independently decompressed on the fly from a variable-rate bitstream by a GPU geometry program with no branches or conditionals. Thus we can store the geometry compressed on the GPU, reducing storage and bandwidth requirements throughout the system. In our rendering approach, only compressed bitstreams and the decoded height values in the view-dependent 'cut' are explicitly stored on the GPU. Normal vectors are computed in a streaming fashion, and remaining geometry and texture coordinates, as well as mesh connectivity, are shared and re-used for all patches. We demonstrate and evaluate our algorithms on a small prototype system in which all compressed geometry fits in the GPU memory and decompression occurs on the fly every rendering frame without any cache maintenance.

99 GENERAL AND MISCELLANEOUS↗

Performance Optimization for Relative-Error-Bounded Lossy Compression on Scientific Data

Scientific simulations in high-performance computing (HPC) environments generate vast volume of data, which may cause a severe I/O bottleneck at runtime and a huge burden on storage space for postanalysis. Unlike traditional data reduction schemes such as deduplication or lossless compression, not only can error-controlled lossy compression significantly reduce the data size but it also holds the promise to satisfy user demand on error control. Pointwise relative error bounds (i.e., compression errors depends on the data values) are widely used by many scientific applications with lossy compression since error control can adapt to the error bound in the dataset automatically. Pointwise relative-error-bounded compression is complicated and time consuming. In this article, we develop efficient precomputation-based mechanisms based on the SZ lossy compression framework. Our mechanisms can avoid costly logarithmic transformation and identify quantization factor values via a fast table lookup, greatly accelerating the relative-error-bounded compression with excellent compression ratios. In addition, we reduce traversing operations for Huffman decoding, significantly accelerating the decompression process in SZ. Experiments with eight well-known real-world scientific simulation datasets show that our solution can improve the compression and decompression rates (i.e., the speed) by about 40 and 80 p, respectively, in most of cases, making our designed lossy compression strategy the best-in-class solution in most cases.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Accelerating Relative-error Bounded Lossy Compression for HPC datasets with Precomputation-Based Mechanisms

Scientific simulations in high-performance computing (HPC) environments are producing vast volume of data, which may cause a severe I/O bottleneck at runtime and a huge burden on storage space for post-analysis. Unlike the traditional data reduction schemes (such as deduplication or lossless compression), not only can error-controlled lossy compression significantly reduce the data size but it can also hold the promise to satisfy user demand on error control. Point-wise relative error bounds (i.e., compression errors depends on the data values) are widely used by many scientific applications in the lossy compression, since error control can adapt to the precision in the dataset automatically. Point-wise relative error bounded compression is complicated and time consuming. In this work, we develop efficient precomputation-based mechanisms in the SZ lossy compression framework. Our mechanisms can avoid costly logarithmic transformation and identify quantization factor values via a fast table lookup, greatly accelerating the relative-error bounded compression with excellent compression ratios. In addition, our mechanisms also help reduce traversing operations for Huffman decoding, and thus significantly accelerate the decompression process in SZ. Experiments with four well-known real-world scientific simulation datasets show that our solution can improve the compression rate by about 30% and decompression rate by about 70% in most of cases, making our designed lossy compression strategy the best choice in class in most cases.

compression rate↗

A lightweight, user-configurable detector ASIC digital architecture with on-chip data compression for MHz X-ray coherent diffraction imaging

Today, most X-ray pixel detectors used at light sources transmit raw pixel data off the detector ASIC. With the availability of more advanced ASIC technology nodes for scientific application, more digital functionalities from the computing domains (e.g., compression) can be integrated directly into a detector ASIC to increase data velocity. In this paper, we describe a lightweight, user-configurable detector ASIC digital architecture with on-chip compression which can be implemented in 130 nm technologies in a reasonable area on the ASIC periphery. In addition, we present a design to efficiently handle the variable data from the stream of parallel compressors. The architecture includes user-selectable lossy and lossless compression blocks. The impact of lossy compression algorithms is evaluated on simulated and experimental X-ray ptychography datasets. This architecture is a practical approach to increase pixel detector frame rates towards the continuous 1 MHz regime for not only coherent imaging techniques such as ptychography, but also for other diffraction techniques at X-ray light sources.

47 OTHER INSTRUMENTATION↗

Optimal Compression of Floating-Point Astronomical Images Without Significant Loss of Information

We describe a compression method for floating-point astronomical images that gives compression ratios of 6 - 10 while still preserving the scientifically important information in the image. The pixel values are first preprocessed by quantizing them into scaled integer intensity levels, which removes some of the uncompressible noise in the image. The integers are then losslessly compressed using the fast and efficient Rice algorithm and stored in a portable FITS format file. Quantizing an image more coarsely gives greater image compression, but it also increases the noise and degrades the precision of the photometric and astrometric measurements in the quantized image. Dithering the pixel values during the quantization process greatly improves the precision of measurements in the more coarsely quantized images. We perform a series of experiments on both synthetic and real astronomical CCD images to quantitatively demonstrate that the magnitudes and positions of stars in the quantized images can be measured with the predicted amount of precision. In order to encourage wider use of these image compression methods, we have made available a pair of general-purpose image compression programs, called fpack and funpack, which can be used to compress any FITS format image.

Pence, William D.↗

DCTune Perceptual Optimization of Compressed Dental X-Rays

In current dental practice, x-rays of completed dental work are often sent to the insurer for verification. It is faster and cheaper to transmit instead digital scans of the x-rays. Further economies result if the images are sent in compressed form. DCTune is a technology for optimizing DCT (digital communication technology) quantization matrices to yield maximum perceptual quality for a given bit-rate, or minimum bit-rate for a given perceptual quality. Perceptual optimization of DCT color quantization matrices. In addition, the technology provides a means of setting the perceptual quality of compressed imagery in a systematic way. The purpose of this research was, with respect to dental x-rays, 1) to verify the advantage of DCTune over standard JPEG (Joint Photographic Experts Group), 2) to verify the quality control feature of DCTune, and 3) to discover regularities in the optimized matrices of a set of images. We optimized matrices for a total of 20 images at two resolutions (150 and 300 dpi) and four bit-rates (0.25, 0.5, 0.75, 1.0 bits/pixel), and examined structural regularities in the resulting matrices. We also conducted psychophysical studies (1) to discover the DCTune quality level at which the images became 'visually lossless,' and (2) to rate the relative quality of DCTune and standard JPEG images at various bitrates. Results include: (1) At both resolutions, DCTune quality is a linear function of bit-rate. (2) DCTune quantization matrices for all images at all bitrates and resolutions are modeled well by an inverse Gaussian, with parameters of amplitude and width. (3) As bit-rate is varied, optimal values of both amplitude and width covary in an approximately linear fashion. (4) Both amplitude and width vary in systematic and orderly fashion with either bit-rate or DCTune quality; simple mathematical functions serve to describe these relationships. (5) In going from 150 to 300 dpi, amplitude parameters are substantially lower and widths larger at corresponding bit-rates or qualities. (6) Visually lossless compression occurs at a DCTune quality value of about 1. (7) At 0.25 bits/pixel, comparative ratings give DCTune a substantial advantage over standard JPEG. As visually lossless bit-rates are approached, this advantage of necessity diminishes. We have concluded that DCTune optimized quantization matrices provide better visual quality than standard JPEG. Meaningful quality levels may be specified by means of the DCTune metric. Optimized matrices are very similar across the class of dental x-rays, suggesting the possibility of a 'class-optimal' matrix. DCTune technology appears to provide some value in the context of compressed dental x-rays.

Watson, Andrew B.↗

Data compression experiments with LANDSAT thematic mapper and Nimbus-7 coastal zone color scanner data

A case study is presented where an image segmentation based compression technique is applied to LANDSAT Thematic Mapper (TM) and Nimbus-7 Coastal Zone Color Scanner (CZCS) data. The compression technique, called Spatially Constrained Clustering (SCC), can be regarded as an adaptive vector quantization approach. The SCC can be applied to either single or multiple spectral bands of image data. The segmented image resulting from SCC is encoded in small rectangular blocks, with the codebook varying from block to block. Lossless compression potential (LDP) of sample TM and CZCS images are evaluated. For the TM test image, the LCP is 2.79. For the CZCS test image the LCP is 1.89, even though when only a cloud-free section of the image is considered the LCP increases to 3.48. Examples of compressed images are shown at several compression ratios ranging from 4 to 15. In the case of TM data, the compressed data are classified using the Bayes' classifier. The results show an improvement in the similarity between the classification results and ground truth when compressed data are used, thus showing that compression is, in fact, a useful first step in the analysis.

Tilton, James C.↗

Transform coding for space applications

Data compression coding requirements for aerospace applications differ somewhat from the compression requirements for entertainment systems. On the one hand, entertainment applications are bit rate driven with the goal of getting the best quality possible with a given bandwidth. Science applications are quality driven with the goal of getting the lowest bit rate for a given level of reconstruction quality. In the past, the required quality level has been nothing less than perfect allowing only the use of lossless compression methods (if that). With the advent of better, faster, cheaper missions, an opportunity has arisen for lossy data compression methods to find a use in science applications as requirements for perfect quality reconstruction runs into cost constraints. This paper presents a review of the data compression problem from the space application perspective. Transform coding techniques are described and some simple, integer transforms are presented. The application of these transforms to space-based data compression problems is discussed. Integer transforms have an advantage over conventional transforms in computational complexity. Space applications are different from broadcast or entertainment in that it is desirable to have a simple encoder (in space) and tolerate a more complicated decoder (on the ground) rather than vice versa. Energy compaction with new transforms are compared with the Walsh-Hadamard (WHT), Discrete Cosine (DCT), and Integer Cosine (ICT) transforms.

Glover, Daniel↗

Progress toward Accelogic compression in ROOT

For the last 7 years, Accelogic pioneered and perfected a radically new theory of numerical computing codenamed “Compressive Computing”, which has an extremely profound impact on real-world computer science [1]. At the core of this new theory is the discovery of one of its fundamental theorems which states that, under very general conditions, the vast majority (typically between 70% and 80%) of the bits used in modern large-scale numerical computations are absolutely irrelevant for the accuracy of the end result. This theory of Compressive Computing provides mechanisms able to identify (with high intelligence and surgical accuracy) the number of bits (i.e., the precision) that can be used to represent numbers without affecting the substance of the end results, as they are computed and vary in real time. The bottom-line outcome will be to provide state-of-the-art compression algorithms --and accompanying software libraries-- able to surpass the performance of the compression engines currently available in the ROOT [7] framework. The resulting technology has the capability to enable substantial economic and operational gains (including speedup) for High Energy and Nuclear Physics data storage/analysis. In our initial studies, a factor of nearly x4 (3.9) compression was achieved with RHIC/STAR data where ROOT compression managed only x1.4 [6].As a collaboration of experimental scientists, private industry, and the ROOT Team, our aim is to capitalize on the substantial success delivered by the initial effort and produce a robust technology properly packaged as an open-source tool that could be used by virtually every experiment around the world as means for improving data management and accessibility.In this contribution, we will present our efforts integrating our concepts of “functionally lossless compression” within the ROOT framework implementation, with the purpose of producing a basic solution readily integrated into HENP applications. We will also present our progress applying this compression through realistic examples of analysis from both the STAR and CMS experiments.

Canal, Ph.↗

Effects of Tunable Data Compression on Geophysical Products Retrieved from Surface Radar Observations with Applications to Spaceborne Meteorological Radars

This paper presents results and analyses of applying an international space data compression standard to weather radar measurements that can easily span 8 orders of magnitude and typically require a large storage capacity as well as significant bandwidth for transmission. By varying the degree of the data compression, we analyzed the non-linear response of models that relate measured radar reflectivity and/or Doppler spectra to the moments and properties of the particle size distribution characterizing clouds and precipitation. Preliminary results for the meteorologically important phenomena of clouds and light rain indicate that for a 0.5 dB calibration uncertainty, typical for the ground-based pulsed-Doppler 94 GHz (or 3.2 mm, W-band) weather radar used as a proxy for spaceborne radar in this study, a lossless compression ratio of only 1.2 is achievable. However, further analyses of the non-linear response of various models of rainfall rate, liquid water content and median volume diameter show that a lossy data compression ratio exceeding 15 is realizable. The exploratory analyses presented are relevant to future satellite missions, where the transmission bandwidth is premium and storage requirements of vast volumes of data, potentially problematic.

cloud properties↗

CSB-RNN: A Faster-Than-Realtime RNN Acceleration Framework with Compressed Structured Blocks

Recurrent Neural Networks (RNN) is widely applied to temporal sequence analysis, where real-time performance is usually in demand. However, RNN suffers a heavy computational workload as the model comes with a large weight matrix. To alleviate the pain, model compression (pruning) schemes have been proposed for RNN that pruning the redundant (near-zero) weight-values. On the one hand, the non-structured pruning methods achieve a considerable pruning rate while bringing the computational irregularity, which is un-friendly to parallel-hardware. On the other hand, the existing structured pruning methods consider the hardware parallelism; However, they suffer a poor pruning rate due to the restrict constraints on pruning structure. This paper presents CSB-RNN, an optimized full-stack RNN framework with the novel compressed structured block (CSB) technique. The CSB-pruned RNN model comes with both fine-granularity that benefits the pruning rate and regular structure that facilitates the hardware-parallelism. Further, we propose a novel hardware architecture for inferencing the CSB-pruned model. Different from conventional parallel hardware, this architecture solves the block-workload imbalance issue and achieves an over 95% hardware utilization. With the experiments on 10 RNN models in 5 application domains, the CSB-RNN realizes 7×-20× lossless compression and up to 50× acceptable lossy-compression, which is 2×-7× to the prior art. With the addition of the novel hardware, the compressed-RNN inference reaches a super real-time latency of 10-400µs with FPGA implementation.

Shi, Runbin↗

Bit Grooming: statistically accurate precision-preserving quantization with compression, evaluated in the netCDF Operators (NCO, v4.4.8+)

Abstract. Geoscientific models and measurements generate false precision (scientifically meaningless data bits) that wastes storage space. False precision can mislead (by implying noise is signal) and be scientifically pointless, especially for measurements. By contrast, lossy compression can be both economical (save space) and heuristic (clarify data limitations) without compromising the scientific integrity of data. Data quantization can thus be appropriate regardless of whether space limitations are a concern. We introduce, implement, and characterize a new lossy compression scheme suitable for IEEE floating-point data. Our new Bit Grooming algorithm alternately shaves (to zero) and sets (to one) the least significant bits of consecutive values to preserve a desired precision. This is a symmetric, two-sided variant of an algorithm sometimes called Bit Shaving that quantizes values solely by zeroing bits. Our variation eliminates the artificial low bias produced by always zeroing bits, and makes Bit Grooming more suitable for arrays and multi-dimensional fields whose mean statistics are important. Bit Grooming relies on standard lossless compression to achieve the actual reduction in storage space, so we tested Bit Grooming by applying the DEFLATE compression algorithm to bit-groomed and full-precision climate data stored in netCDF3, netCDF4, HDF4, and HDF5 formats. Bit Grooming reduces the storage space required by initially uncompressed and compressed climate data by 25–80 and 5–65 %, respectively, for single-precision values (the most common case for climate data) quantized to retain 1–5 decimal digits of precision. The potential reduction is greater for double-precision datasets. When used aggressively (i.e., preserving only 1–2 digits), Bit Grooming produces storage reductions comparable to other quantization techniques such as Linear Packing. Unlike Linear Packing, whose guaranteed precision rapidly degrades within the relatively narrow dynamic range of values that it can compress, Bit Grooming guarantees the specified precision throughout the full floating-point range. Data quantization by Bit Grooming is irreversible (i.e., lossy) yet transparent, meaning that no extra processing is required by data users/readers. Hence Bit Grooming can easily reduce data storage volume without sacrificing scientific precision or imposing extra burdens on users.

58 GEOSCIENCES↗