The global phenomenon of forest degradation is a pressing issue with severe implications for climate stability and biodiversity protection. In this work we generate Bayesian updating deforestation detection (BUDD) algorithms by incorporating Sentinel-1 backscatter and interferometric coherence with Sentinel-2 normalized vegetation index data. We show that the algorithm provides good performance in validation AOIs. We compare the effectiveness of different combinations of the three data modalities as inputs into the BUDD algorithm and compare against existing benchmarks based on optical imagery.

We consider the problem of unwrapping the phase of two-dimensional interferograms, and adopt a known formulation as a sparse optimization problem. Many algorithms have been developed for solving sparse optimization problems that occur in the field of compressive sensing; in this work, we adapt one such algorithm for use in the unwrapping problem. The result is an unwrapping algorithm that gives very similar results to those of existing algorithms, but that is simpler, more reliable, and more computationally efficient.

This paper presents a prototype crop production monitoring pipeline which identifies agricultural fields planted with small grains over 19 countries in the Middle East and North Africa (MENA) and monitors those crops over the growing season. The technical approach employs an boundary-based image segmentation algorithm to define units of consistent land use, and clusters Sentinel-2 normalized difference vegetation index (NDVI) time series within the fields to identify small grains, without requiring labeled examples. The small grain fields are then monitored over the growing season on a monthly basis using time-integrated NDVI beginning at an interval from the planting date to the end of the target month. Classification accuracy is estimated at 82% for the test case, and crop deviations from the mean and/or reference year(s) have been detected within 1-2 months of planting, and are reliably detected several months before harvest.

Although monitoring forest disturbance is crucial to understanding atmospheric carbon accumulation and biodiversity loss, persistent cloud cover, especially in tropical areas, makes detecting forest disturbances using optical remotely sensed imagery difficult. In Sentinel-1 synthetic aperture radar (SAR) images, forest clearings exhibit reduced backscatter as well as increased interferometric coherence. We combined SAR and Interferometric SAR metrics from Sentinel-1 data collected in Borneo between in 2017 and 2018 and applied unsupervised change detection methods to the time series. The results show that a simple log-ratio based detector performs similarly to a more sophisticated anomalous change detection algorithm. The log-ratio detector was deployed to compare a 2017 mean Sentinel-1 composite with a 2018 mean composite. Approximately 20000 newly deforested areas were identified in 2018, for a total of 3000 km2 . The findings suggest that leveraging SAR data to monitor deforestation has the potential to achieve better performance than Global Forest Watch, the current Landsat based gold standard. Future work will leverage the short revisit time (6-12 days) of Sentinel-1 as an opportunity for continuous monitoring of deforestation. The improved time resolution associated with SAR observations in cloudy regions might enable the identification of areas at risk of deforestation early enough in the clearing process to allow preventive actions to be taken.

The European Space Agency’s Sentinel 1 satellite acquires global synthetic aperture radar (SAR) data, making it particularly well-suited for analyzing tropical regions that may be covered in clouds and therefore concealed from optical data. Here, we focus our attention on rice, a predominant crop in the tropics, and leverage Sentinel 1 data to identify field boundaries, classify fields as rice or not rice, and estimate the number of times each rice field is harvested during a year. Using the Descartes Labs Platform to conduct this analysis allows us to scale our models to run across Asia, providing a region-wide analysis of rice extent and management.

We consider the problem of unwrapping the phase of synthetic aperture radar interferograms. Like several existing approaches, we use an estimate of the gradient of the interferogram phase. Our contribution is to regularize this differentiation process, in a manner that both suppresses noise and allows the estimate to be discontinuous. This allows us to preserve the elevation information present in the phase data, without smoothing away the discontinuities created by phase wrapping. We demonstrate the differentiation with a simple phase unwrapping approach, and apply it to an example interferogram computed from Sentinel-l image data.

The recent computing performance revolution has driven improvements in sensor, communication, and storage technology. Multi-decadal remote sensing datasets at the petabyte scale are now available in commercial clouds, with new satellite constellations generating petabytes/year of daily high-resolution global coverage imagery. Cloud computing and storage, combined with recent advances in machine learning, are enabling understanding of the world at a scale and at a level of detail never before feasible. We present results from an ongoing effort to develop satellite imagery analysis tools that aggregate temporal, spatial, and spectral information and that can scale with the high-rate and dimensionality of imagery being collected. We focus on the problem of monitoring food crop productivity across the Middle East and North Africa, and show how an analysis-ready, multi-sensor data platform enables quick prototyping of satellite imagery analysis algorithms, from land use/land cover classification and natural resource mapping, to yearly and monthly vegetative health change trends at the structural field level.

Synthetic aperture radar (SAR) can penetrate clouds, rendering these data particularly useful for mapping land cover and land use in tropical areas. In this study, we leverage the image processing and analysis platform built at Descartes Labs to analyze a time-series of Sentinel-1 SAR data acquired during the 2014 - 2015 growing season across the Vietnamese Mekong River Delta, a region that is dominated by rice paddy agriculture. Rice is a staple food for the majority of the global population, but production is threatened by expanding urban areas, rising temperatures, and encroaching sea levels. Most of the world's rice is grown in the monsoonal tropics, and frequent cloud cover makes monitoring the landscape challenging. Here, we illustrate how the unique phenology of rice is captured with SAR data to accurately map annual rice paddy extent, and we show how the method can be extended to also determine the amount of rice grown during each growing period within a season.

We consider the problem of differentiating a multivariable function specified by noisy data. Following previous work for the single-variable case, we regularize the differentiation process, by formulating it as an inverse problem with an integration operator as the forward model. Total-variation regularization avoids the noise amplification of finite-difference methods, while allowing for discontinuous solutions. Unlike the single-variable case, we use an alternating directions, method of multipliers algorithm to provide greater efficiency for large problems. We apply the method to synthetic data and to synthetic-aperture radar satellite imagery.

The increase in performance, availability, and coverage of multispectral satellite sensor constellations has led to a drastic increase in data volume and data rate. Multi-decadal remote sensing datasets at the petabyte scale are now available in commercial clouds, with new satellite constellations generating petabytes/year of daily high-resolution global coverage imagery. The data analysis capability, however, has lagged behind storage and compute developments, and has traditionally focused on individual scene processing. We present results from an ongoing effort to develop satellite imagery analysis tools that aggregate temporal, spatial, and spectral information and can scale with the high-rate and dimensionality of imagery being collected. We investigate and compare the performance of pixel-level crop identification using tree-based classifiers and its dependence on both temporal and spectral features. Classification performance is assessed using as ground-truth Cropland Data Layer (CDL) crop masks generated by the US Department of Agriculture (USDA). The CDL maps contain 30m spatial resolution, pixel-level labels for around 200 categories of land cover, but are however only available post-growing season. The analysis focuses on McCook county in South Dakota and shows crop classification using a temporal stack of Landsat 8 (L8) imagery over the growing season, from April through October. Specifically, we consider the temporal L8 stack depth, as well as different normalized band difference indices, and evaluate their contribution to crop identification. We also show an extension of our algorithm to map corn and soy crops in the state of Mato Grosso, Brazil.

The recent computing performance revolution has driven improvements in sensor, communication, and storage technology. Multi-decadal remote sensing datasets at the petabyte scale are now available in commercial clouds, with new satellite constellations generating petabytes/year of daily high-resolution global coverage imagery. Cloud computing and storage, combined with recent advances in machine learning, are enabling understanding of the world at a scale and at a level of detail never before feasible. We show data processing at terabyte rates in the cloud using multi-modal sensor data and use the calibrated, georeferenced imagery to build videos of the Earth at varying temporal and spatial resolutions. Such temporal-spectral-spatial views of the world enable a range of climate monitoring and change-detection applications. Here we demonstrate one application by using MODIS satellite imagery temporal stacks to classify land cover over North America, and explore the use of synthetic aperture imagery (SAR) to enhance the resulting category mask.

Nonconvex regularization functions such as the l(p) quasinorm (0 < p < 1) can recover sparser solutions from fewer measurements than the convex l(1) regularization function. They have been widely used for compressive sensing and signal processing. This chapter briefly reviews the development of algorithms for nonconvex regularization. Because nonconvex regularization usually has different regularity properties from other functions in a problem, we often apply operator splitting (forward-backward splitting) to develop algorithms that treat them separately. The treatment on nonconvex regularization is via the proximal mapping. We also review another class of coordinate descent algorithms that work for both convex and nonconvex functions. They split variables into small, possibly parallel, subproblems, each of which updates a variable while fixing others. Their theory and applications have been recently extended to cover nonconvex regularization functions, which we review in this chapter. Finally, we also briefly mention an ADMM-based algorithm for nonconvex regularization, as well as the recent algorithms for the so-called nonconvex sort l(1) and l(1)-l(2) minimization.

The availability of high-resolution digital elevation data (submeter resolution) from LiDAR has increased dramatically over the past few years. As a result, the efficient storage and transmission of those large data sets and their use for geomorphic feature extraction and hydrologic/environmental modeling are becoming a scientific challenge. This letter explores the use of multiresolution wavelet analysis for compression of LiDAR digital elevation data sets. The compression takes advantage of the fact that, in most landscapes, neighboring pixels are correlated and thus contain some redundant information. The space-frequency localization of the wavelet filters allows one to preserve detailed high-resolution features where needed while representing the rest of the landscape at lower resolution. We explore a lossy compression methodology based on biorthogonal wavelets and demonstrate that, by keeping only approximately 10% of the original information (data compression ratio ~94%), the reconstructed landscapes retain most of the information of relevance to geomorphologic applications, such as the ability to accurately extract channel networks for environmental flux routing, as well as to identify geomorphic process transition from the curvature-slope and slope-distance relationships.

The ℓ 0 minimization of compressed sensing is often relaxed to ℓ 1 , which yields easy computation using the shrinkage mapping known as soft thresholding, and can be shown to recover the original solution under certain hypotheses. Recent work has derived a general class of shrinkages and associated nonconvex penalties that better approximate the original ℓ 0 penalty and empirically can recover the original solution from fewer measurements. We specifically examine p-shrinkage and firm thresholding. In this work, we prove that given data and a measurement matrix from a broad class of matrices, one can choose parameters for these classes of shrinkages to guarantee exact recovery of the sparsest solution. We further prove convergence of the algorithm iterative p-shrinkage (IPS) for solving one such relaxed problem.

We present our experiences using cloud computing to support data-intensive analytics on satellite imagery for commercial applications. Drawing from our background in highperformance computing, we draw parallels between the early days of clustered computing systems and the current state of cloud computing and its potential to disrupt the HPC market. Using our own virtual file system layer on top of cloud remote object storage, we demonstrate aggregate read bandwidth of 230 gigabytes per second using 512 Google Compute Engine (GCE) nodes accessing a USA multi-region standard storage bucket. This figure is comparable to the best HPC storage systems in existence. We also present several of our application results, including the identification of field boundaries in Ukraine, and the generation of a global cloud-free base layer from Landsat imagery.