The availability of well-curated datasets has driven the success of Machine Learning (ML) models. Despite the increased access to earth observation data for agriculture, there is a scarcity of curated, labelled datasets, which limits the potential of its use in training ML models for remote sensing (RS) in agriculture. To this end, we introduce a first-of-its-kind dataset, SICKLE, having time-series images at different spatial resolutions from 3 different satellites, annotated with multiple key cropping parameters for paddy cultivation for the Cauvery Delta region in Tamil Nadu, India. The dataset comprises of 2,398 season-wise samples from 388 unique plots distributed across 4 districts of the Delta. The dataset covers multi-spectral, thermal and microwave data between the time period January 2018-March 2021. The paddy samples are annotated with 4 key cropping parameters, i.e. sowing date, transplanting date, harvesting date and crop yield. This is one of the first studies to consider the growing season (using sowing and harvesting dates) as part of a dataset. We also propose a yield prediction strategy that uses time-series data generated based on the observed growing season and the standard seasonal information obtained from Tamil Nadu Agricultural University for the region. The consequent performance improvement highlights the impact of ML techniques that leverage domain knowledge that are consistent with standard practices followed by farmers in a specific region. We benchmark the dataset on 3 separate tasks, namely crop type, phenology date (sowing, transplanting, harvesting) and yield prediction, and develop an end-to-end framework for predicting key crop parameters in a real-world setting.

Crop residue burning is a major source of air pollution in many parts of the world, notably South Asia. Policymakers, practitioners and researchers have invested in both measuring impacts and developing interventions to reduce burning. However, measuring the impacts of burning or the effectiveness of interventions to reduce burning requires data on where burning occurred. These data are challenging to collect in the field, both in terms of cost and feasibility. We take advantage of data from ground-based monitoring of crop residue burning in Punjab, India to explore whether burning can be detected more effectively using accessible satellite imagery. Specifically, we used 3m PlanetScope data with high temporal resolution (up to daily) as well as publicly-available Sentinel-2 data with weekly temporal resolution but greater depth of spectral information. Following an analysis of the ability of different spectral bands and burn indices to separate burned and unburned plots individually, we built a Random Forest model with those determined to provide the greatest separability and evaluated model performance with ground-verified data. Our overall model accuracy of 82-percent is favorable given the challenges presented by the measurement. Based on insights from this process, we discuss technical challenges of detecting crop residue burning from satellite imagery as well as challenges to measuring impacts, both of burning and of policy interventions.

Remotely sensed geospatial data are critical for applications including precision agriculture, urban planning, disaster monitoring and response, and climate change research, among others. Deep learning methods are particularly promising for modeling many remote sensing tasks given the success of deep neural networks in similar computer vision tasks and the sheer volume of remotely sensed imagery available. However, the variance in data collection methods and handling of geospatial metadata make the application of deep learning methodology to remotely sensed data nontrivial. For example, satellite imagery often includes additional spectral bands beyond red, green, and blue and must be joined to other geospatial data sources that can have differing coordinate systems, bounds, and resolutions. To help realize the potential of deep learning for remote sensing applications, we introduce TorchGeo, a Python library for integrating geospatial data into the PyTorch deep learning ecosystem. TorchGeo provides data loaders for a variety of benchmark datasets, composable datasets for generic geospatial data sources, samplers for geospatial data, and transforms that work with multispectral imagery. TorchGeo is also the first library to provide pre-trained models for multispectral satellite imagery (e.g., models that use all bands from the Sentinel-2 satellites), allowing for advances in transfer learning on downstream remote sensing tasks with limited labeled data. We use TorchGeo to create reproducible benchmark results on existing datasets and benchmark our proposed method for preprocessing geospatial imagery on the fly. TorchGeo is open source and available on GitHub: https://github.com/microsoft/torchgeo.

Deep learning has become one of remote sensing scientists' most efficient computer vision tools in recent years. However, the lack of training labels for the remote sensing datasets means that scientists need to solve the domain adaptation problem to narrow the discrepancy between satellite image datasets. As a result, image segmentation models that are then trained, could better generalize and use an existing set of labels instead of requiring new ones. This work proposes an unsupervised domain adaptation model that preserves semantic consistency and per-pixel quality for the images during the style-transferring phase. This paper's major contribution is proposing the improved architecture of the SemI2I model, which significantly boosts the proposed model's performance and makes it competitive with the state-of-the-art CyCADA model. A second contribution is testing the CyCADA model on the remote sensing multi-band datasets such as WorldView-2 and SPOT-6. The proposed model preserves semantic consistency and per-pixel quality for the images during the style-transferring phase. Thus, the semantic segmentation model, trained on the adapted images, shows substantial performance gain compared to the SemI2I model and reaches similar results as the state-of-the-art CyCADA model. The future development of the proposed method could include ecological domain transfer, {\em a priori} evaluation of dataset quality in terms of data distribution, or exploration of the inner architecture of the domain adaptation model.

Despite the plethora of successful Super-Resolution Reconstruction (SRR) models applied to natural images, their application to remote sensing imagery tends to produce poor results. Remote sensing imagery is often more complicated than natural images and has its peculiarities such as being of lower resolution, it contains noise, and often depicting large textured surfaces. As a result, applying non-specialized SRR models on remote sensing imagery results in artifacts and poor reconstructions. To address these problems, this paper proposes an architecture inspired by previous research work, introducing a novel approach for forcing an SRR model to output realistic remote sensing images: instead of relying on feature-space similarities as a perceptual loss, the model considers pixel-level information inferred from the normalized Digital Surface Model (nDSM) of the image. This strategy allows the application of better-informed updates during the training of the model which sources from a task (elevation map inference) that is closely related to remote sensing. Nonetheless, the nDSM auxiliary information is not required during production and thus the model infers a super-resolution image without any additional data besides its low-resolution pairs. We assess our model on two remotely sensed datasets of different spatial resolutions that also contain the DSM pairs of the images: the DFC2018 dataset and the dataset containing the national Lidar fly-by of Luxembourg. Based on visual inspection, the inferred super-resolution images exhibit particularly superior quality. In particular, the results for the high-resolution DFC2018 dataset are realistic and almost indistinguishable from the ground truth images.

Albedo, a company developing low-flying satellites that will deliver ultra high resolution images, announced a $48M Series A financing round co-led by Breakthrough Energy Ventures and Shield Capital, bringing the company's total funding to $58M in less than two years since inception. "Albedo is developing the world's first commercially available high-resolution imaging capability, which holds tremendous promise for both commercial and defense customers," said Raj Shah, Managing Director of Shield Capital Participation in the round included new investors Republic Capital, Giant Step Capital, and C16 Ventures, along with existing investors Initialized Capital, Joe Montana's Liquid 2, Kevin Mahaffey, and other undisclosed participants. Albedo is developing very-low-earth-orbit (VLEO) satellites that will co-collect 10 centimeter (cm) optical imagery and 2 meter thermal infrared imagery. The resolution of Albedo's imagery is unprecedented in the commercial market and will enable applications that have been limited by lower resolution satellites or operational limitations of imagery collected from planes. The Series A funding will enable the company to complete development of its first satellite and develop the software to support satellite operations and deliver imagery to users.

Self-supervised methods have shown tremendous success in the field of computer vision, including applications in remote sensing and medical imaging. Most popular contrastive-loss based methods like SimCLR, MoCo, MoCo-v2 use multiple views of the same image by applying contrived augmentations on the image to create positive pairs and contrast them with negative examples. Although these techniques work well, most of these techniques have been tuned on ImageNet (and similar computer vision datasets). While there have been some attempts to capture a richer set of deformations in the positive samples, in this work, we explore a promising alternative to generating positive examples for remote sensing data within the contrastive learning framework. Images captured from different sensors at the same location and nearby timestamps can be thought of as strongly augmented instances of the same scene, thus removing the need to explore and tune a set of hand crafted strong augmentations. In this paper, we propose a simple dual-encoder framework, which is pre-trained on a large unlabeled dataset (~1M) of Sentinel-1 and Sentinel-2 image pairs. We test the embeddings on two remote sensing downstream tasks: flood segmentation and land cover mapping, and empirically show that embeddings learnt from this technique outperform the conventional technique of collecting positive examples via aggressive data augmentations.

Satellite remote sensing presents a cost-effective solution for synoptic flood monitoring, and satellite-derived flood maps provide a computationally efficient alternative to numerical flood inundation models traditionally used. While satellites do offer timely inundation information when they happen to cover an ongoing flood event, they are limited by their spatiotemporal resolution in terms of their ability to dynamically monitor flood evolution at various scales. Constantly improving access to new satellite data sources as well as big data processing capabilities has unlocked an unprecedented number of possibilities in terms of data-driven solutions to this problem. Specifically, the fusion of data from satellites, such as the Copernicus Sentinels, which have high spatial and low temporal resolution, with data from NASA SMAP and GPM missions, which have low spatial but high temporal resolutions could yield high-resolution flood inundation at a daily scale. Here a Convolutional-Neural-Network is trained using flood inundation maps derived from Sentinel-1 Synthetic Aperture Radar and various hydrological, topographical, and land-use based predictors for the first time, to predict high-resolution probabilistic maps of flood inundation. The performance of UNet and SegNet model architectures for this task is evaluated, using flood masks derived from Sentinel-1 and Sentinel-2, separately with 95 percent-confidence intervals. The Area under the Curve (AUC) of the Precision Recall Curve (PR-AUC) is used as the main evaluation metric, due to the inherently imbalanced nature of classes in a binary flood mapping problem, with the best model delivering a PR-AUC of 0.85.

Remote sensor image object detection is an important technology for Earth observation, and is used in various tasks such as forest fire monitoring and ocean monitoring. Image object detection technology, despite the significant developments, is struggling to handle remote sensor images and small-scale objects, due to the limited pixels of small objects. Numerous existing studies have demonstrated that an effective way to promote small object detection is to introduce the spatial context. Meanwhile, recent researches for image classification have shown that spectral convolution operations can perceive long-term spatial dependence more efficiently in the frequency domain than spatial domain. Inspired by this observation, we propose a Frequency-aware Feature Pyramid Framework (FFPF) for remote sensing object detection, which consists of a novel Frequency-aware ResNet (F-ResNet) and a Bilateral Spectral-aware Feature Pyramid Network (BS-FPN). Specifically, the F-ResNet is proposed to perceive the spectral context information by plugging the frequency domain convolution into each stage of the backbone, extracting richer features of small objects. To the best of our knowledge, this is the first work to introduce frequency-domain convolution into remote sensing object detection task. In addition, the BSFPN is designed to use a bilateral sampling strategy and skipping connection to better model the association of object features at different scales, towards unleashing the potential of the spectral context information from F-ResNet. Extensive experiments are conducted for object detection in the optical remote sensing image dataset (DIOR and DOTA). The experimental results demonstrate the excellent performance of our method. It achieves an average accuracy (mAP) without any tricks.

Accurate prediction of crop yield before harvest is of great importance for crop logistics, market planning, and food distribution around the world. Yield prediction requires monitoring of phenological and climatic characteristics over extended time periods to model the complex relations involved in crop development. Remote sensing satellite images provided by various satellites circumnavigating the world are a cheap and reliable way to obtain data for yield prediction. The field of yield prediction is currently dominated by Deep Learning approaches. While the accuracies reached with those approaches are promising, the needed amounts of data and the ``black-box'' nature can restrict the application of Deep Learning methods. The limitations can be overcome by proposing a pipeline to process remote sensing images into feature-based representations that allow the employment of Extreme Gradient Boosting (XGBoost) for yield prediction. A comparative evaluation of soybean yield prediction within the United States shows promising prediction accuracies compared to state-of-the-art yield prediction systems based on Deep Learning. Feature importances expose the near-infrared spectrum of light as an important feature within our models. The reported results hint at the capabilities of XGBoost for yield prediction and encourage future experiments with XGBoost for yield prediction on other crops in regions all around the world.