Anthony Ortiz

Van Anh Le, Varshini Reddy, Zixi Chen et al.

In this paper we propose a mask-conditional synthetic image generation model for creating synthetic satellite imagery datasets. Given a dataset of real high-resolution images and accompanying land cover masks, we show that it is possible to train an upstream conditional synthetic imagery generator, use that generator to create synthetic imagery with the land cover masks, then train a downstream model on the synthetic imagery and land cover masks that achieves similar test performance to a model that was trained with the real imagery. Further, we find that incorporating a mixture of real and synthetic imagery acts as a data augmentation method, producing better models than using only real imagery (0.5834 vs. 0.5235 mIoU). Finally, we find that encouraging diversity of outputs in the upstream model is a necessary component for improved downstream task performance. We have released code for reproducing our work on GitHub, see https://github.com/ms-synthetic-satellite-image/synthetic-satellite-imagery .

Caleb Robinson, Anthony Ortiz, Hogeun Park et al.

Innovations in computer vision algorithms for satellite image analysis can enable us to explore global challenges such as urbanization and land use change at the planetary level. However, domain shift problems are a common occurrence when trying to replicate models that drive these analyses to new areas, particularly in the developing world. If a model is trained with imagery and labels from one location, then it usually will not generalize well to new locations where the content of the imagery and data distributions are different. In this work, we consider the setting in which we have a single large satellite imagery scene over which we want to solve an applied problem -- building footprint segmentation. Here, we do not necessarily need to worry about creating a model that generalizes past the borders of our scene but can instead train a local model. We show that surprisingly few labels are needed to solve the building segmentation problem with very high-resolution (0.5m/px) satellite imagery with this setting in mind. Our best model trained with just 527 sparse polygon annotations (an equivalent of 1500 x 1500 densely labeled pixels) has a recall of 0.87 over held out footprints and a R2 of 0.93 on the task of counting the number of buildings in 200 x 200-meter windows. We apply our models over high-resolution imagery in Amman, Jordan in a case study on urban change detection.

Caleb Robinson, Simone Fobi Nsutezo, Anthony Ortiz et al.

Rapid and accurate building damage assessments from high-resolution satellite imagery following a natural disaster is essential to inform and optimize first responder efforts. However, performing such building damage assessments in an automated manner is non-trivial due to the challenges posed by variations in disaster-specific damage, diversity in satellite imagery, and the dearth of extensive, labeled datasets. To circumvent these issues, this paper introduces a human-in-the-loop workflow for rapidly training building damage assessment models after a natural disaster. This article details a case study using this workflow, executed in partnership with the American Red Cross during a tornado event in Rolling Fork, Mississippi in March, 2023. The output from our human-in-the-loop modeling process achieved a precision of 0.86 and recall of 0.80 for damaged buildings when compared to ground truth data collected post-disaster. This workflow was implemented end-to-end in under 2 hours per satellite imagery scene, highlighting its potential for real-time deployment.

Simone Fobi, Manuel Cardona, Elliott Collins et al.

This work presents an approach for combining household demographic and living standards survey questions with features derived from satellite imagery to predict the poverty rate of a region. Our approach utilizes visual features obtained from a single-step featurization method applied to freely available 10m/px Sentinel-2 surface reflectance satellite imagery. These visual features are combined with ten survey questions in a proxy means test (PMT) to estimate whether a household is below the poverty line. We show that the inclusion of visual features reduces the mean error in poverty rate estimates from 4.09% to 3.88% over a nationally representative out-of-sample test set. In addition to including satellite imagery features in proxy means tests, we propose an approach for selecting a subset of survey questions that are complementary to the visual features extracted from satellite imagery. Specifically, we design a survey variable selection approach guided by the full survey and image features and use the approach to determine the most relevant set of small survey questions to include in a PMT. We validate the choice of small survey questions in a downstream task of predicting the poverty rate using the small set of questions. This approach results in the best performance -- errors in poverty rate decrease from 4.09% to 3.71%. We show that extracted visual features encode geographic and urbanization differences between regions.

Caleb Robinson, Isaac Corley, Anthony Ortiz et al.

Fully understanding a complex high-resolution satellite or aerial imagery scene often requires spatial reasoning over a broad relevant context. The human object recognition system is able to understand object in a scene over a long-range relevant context. For example, if a human observes an aerial scene that shows sections of road broken up by tree canopy, then they will be unlikely to conclude that the road has actually been broken up into disjoint pieces by trees and instead think that the canopy of nearby trees is occluding the road. However, there is limited research being conducted to understand long-range context understanding of modern machine learning models. In this work we propose a road segmentation benchmark dataset, Chesapeake Roads Spatial Context (RSC), for evaluating the spatial long-range context understanding of geospatial machine learning models and show how commonly used semantic segmentation models can fail at this task. For example, we show that a U-Net trained to segment roads from background in aerial imagery achieves an 84% recall on unoccluded roads, but just 63.5% recall on roads covered by tree canopy despite being trained to model both the same way. We further analyze how the performance of models changes as the relevant context for a decision (unoccluded roads in our case) varies in distance. We release the code to reproduce our experiments and dataset of imagery and masks to encourage future research in this direction -- https://github.com/isaaccorley/ChesapeakeRSC.

Keiller Nogueira, Akram Zaytar, Wanli Ma et al.

The increasing accessibility of remotely sensed data and the potential of such data to inform large-scale decision-making has driven the development of deep learning models for many Earth Observation tasks. Traditionally, such models must be trained on large datasets. However, the common assumption that broadly larger datasets lead to better outcomes tends to overlook the complexities of the data distribution, the potential for introducing biases and noise, and the computational resources required for processing and storing vast datasets. Therefore, effective solutions should consider both the quantity and quality of data. In this paper, we propose six novel core-set selection methods for selecting important subsets of samples from remote sensing image segmentation datasets that rely on imagery only, labels only, and a combination of each. We benchmark these approaches against a random-selection baseline on three commonly used land cover classification datasets: DFC2022, Vaihingen, and Potsdam. In each of the datasets, we demonstrate that training on a subset of samples outperforms the random baseline, and some approaches outperform training on all available data. This result shows the importance and potential of data-centric learning for the remote sensing domain. The code is available at https://github.com/keillernogueira/data-centric-rs-classification/.

Adam J. Stewart, Caleb Robinson, Isaac A. Corley et al.

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.

Isaac Corley, Caleb Robinson, Anthony Ortiz

In recent years, there has been an explosion of proposed change detection deep learning architectures in the remote sensing literature. These approaches claim to offer state-of-the-art performance on different standard benchmark datasets. However, has the field truly made significant progress? In this paper we perform experiments which conclude a simple U-Net segmentation baseline without training tricks or complicated architectural changes is still a top performer for the task of change detection.

Caleb Robinson, Anthony Ortiz, Allen Kim et al.

We present a comprehensive global temporal dataset of commercial solar photovoltaic (PV) farms and onshore wind turbines, derived from high-resolution satellite imagery analyzed quarterly from the fourth quarter of 2017 to the second quarter of 2024. We create this dataset by training deep learning-based segmentation models to identify these renewable energy installations from satellite imagery, then deploy them on over 13 trillion pixels covering the world. For each detected feature, we estimate the construction date and the preceding land use type. This dataset offers crucial insights into progress toward sustainable development goals and serves as a valuable resource for policymakers, researchers, and stakeholders aiming to assess and promote effective strategies for renewable energy deployment. Our final spatial dataset includes 375,197 individual wind turbines and 86,410 solar PV installations. We aggregate our predictions to the country level -- estimating total power capacity based on construction date, solar PV area, and number of windmills -- and find an $r^2$ value of $0.96$ and $0.93$ for solar PV and onshore wind respectively compared to IRENA's most recent 2023 country-level capacity estimates.

Isaac Corley, Simone Fobi Nsutezo, Anthony Ortiz et al.

Remote sensing imagery is dense with objects and contextual visual information. There is a recent trend to combine paired satellite images and text captions for pretraining performant encoders for downstream tasks. However, while contrastive image-text methods like CLIP enable vision-language alignment and zero-shot classification ability, vision-only downstream performance tends to degrade compared to image-only pretraining, such as MAE. In this paper, we propose FLAVARS, a pretraining method that combines the best of both contrastive learning and masked modeling, along with geospatial alignment via contrastive location encoding. We find that FLAVARS significantly outperforms a baseline of SkyCLIP for vision-only tasks such as KNN classification and semantic segmentation, +6\% mIOU on SpaceNet1, while retaining the ability to perform zero-shot classification, unlike MAE pretrained methods.

Simone Fobi Nsutezo, Amrita Gupta, Duncan Kebut et al.

As of 2023, a record 117 million people have been displaced worldwide, more than double the number from a decade ago [22]. Of these, 32 million are refugees under the UNHCR mandate, with 8.7 million residing in refugee camps. A critical issue faced by these populations is the lack of access to electricity, with 80% of the 8.7 million refugees and displaced persons in camps globally relying on traditional biomass for cooking and lacking reliable power for essential tasks such as cooking and charging phones. Often, the burden of collecting firewood falls on women and children, who frequently travel up to 20 kilometers into dangerous areas, increasing their vulnerability.[7] Electricity access could significantly alleviate these challenges, but a major obstacle is the lack of accurate power grid infrastructure maps, particularly in resource-constrained environments like refugee camps, needed for energy access planning. Existing power grid maps are often outdated, incomplete, or dependent on costly, complex technologies, limiting their practicality. To address this issue, PGRID is a novel application-based approach, which utilizes high-resolution aerial imagery to detect electrical poles and segment electrical lines, creating precise power grid maps. PGRID was tested in the Turkana region of Kenya, specifically the Kakuma and Kalobeyei Camps, covering 84 km2 and housing over 200,000 residents. Our findings show that PGRID delivers high-fidelity power grid maps especially in unplanned settlements, with F1-scores of 0.71 and 0.82 for pole detection and line segmentation, respectively. This study highlights a practical application for leveraging open data and limited labels to improve power grid mapping in unplanned settlements, where the growing number of displaced persons urgently need sustainable energy infrastructure solutions.

Anthony Ortiz, Dhaval Negandhi, Sagar R Mysorekar et al.

Rapid development of renewable energy sources, particularly solar photovoltaics (PV), is critical to mitigate climate change. As a result, India has set ambitious goals to install 500 gigawatts of solar energy capacity by 2030. Given the large footprint projected to meet renewables energy targets, the potential for land use conflicts over environmental values is high. To expedite development of solar energy, land use planners will need access to up-to-date and accurate geo-spatial information of PV infrastructure. In this work, we developed a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery with a mean accuracy of 92%. Our model predictions were validated by human experts to obtain a dataset of 1363 solar PV farms. Using this dataset, we measure the solar footprint across India and quantified the degree of landcover modification associated with the development of PV infrastructure. Our analysis indicates that over 74% of solar development In India was built on landcover types that have natural ecosystem preservation, or agricultural value.

Caleb Robinson, Anthony Ortiz, Lacey Hughey et al.

Localizing and counting large ungulates -- hoofed mammals like cows and elk -- in very high-resolution satellite imagery is an important task for supporting ecological studies. Prior work has shown that this is feasible with deep learning based methods and sub-meter multi-spectral satellite imagery. We extend this line of work by proposing a baseline method, CowNet, that simultaneously estimates the number of animals in an image (counts), as well as predicts their location at a pixel level (localizes). We also propose an methodology for evaluating such models on counting and localization tasks across large scenes that takes the uncertainty of noisy labels and the information needed by stakeholders in ecological monitoring tasks into account. Finally, we benchmark our baseline method with state of the art vision methods for counting objects in scenes. We specifically test the temporal generalization of the resulting models over a large landscape in Point Reyes Seashore, CA. We find that the LC-FCN model performs the best and achieves an average precision between 0.56 and 0.61 and an average recall between 0.78 and 0.92 over three held out test scenes.

Caleb Robinson, Anthony Ortiz, Juan M. Lavista Ferres et al.

Longitudinal studies are vital to understanding dynamic changes of the planet, but labels (e.g., buildings, facilities, roads) are often available only for a single point in time. We propose a general model, Temporal Cluster Matching (TCM), for detecting building changes in time series of remotely sensed imagery when footprint labels are observed only once. The intuition behind the model is that the relationship between spectral values inside and outside of building's footprint will change when a building is constructed (or demolished). For instance, in rural settings, the pre-construction area may look similar to the surrounding environment until the building is constructed. Similarly, in urban settings, the pre-construction areas will look different from the surrounding environment until construction. We further propose a heuristic method for selecting the parameters of our model which allows it to be applied in novel settings without requiring data labeling efforts (to fit the parameters). We apply our model over a dataset of poultry barns from 2016/2017 high-resolution aerial imagery in the Delmarva Peninsula and a dataset of solar farms from a 2020 mosaic of Sentinel 2 imagery in India. Our results show that our model performs as well when fit using the proposed heuristic as it does when fit with labeled data, and further, that supervised versions of our model perform the best among all the baselines we test against. Finally, we show that our proposed approach can act as an effective data augmentation strategy -- it enables researchers to augment existing structure footprint labels along the time dimension and thus use imagery from multiple points in time to train deep learning models. We show that this improves the spatial generalization of such models when evaluated on the same change detection task.

Jean-Francois Rajotte, Sumit Mukherjee, Caleb Robinson et al.

We introduce FELICIA (FEderated LearnIng with a CentralIzed Adversary) a generative mechanism enabling collaborative learning. In particular, we show how a data owner with limited and biased data could benefit from other data owners while keeping data from all the sources private. This is a common scenario in medical image analysis where privacy legislation prevents data from being shared outside local premises. FELICIA works for a large family of Generative Adversarial Networks (GAN) architectures including vanilla and conditional GANs as demonstrated in this work. We show that by using the FELICIA mechanism, a data owner with limited image samples can generate high-quality synthetic images with high utility while neither data owners has to provide access to its data. The sharing happens solely through a central discriminator that has access limited to synthetic data. Here, utility is defined as classification performance on a real test set. We demonstrate these benefits on several realistic healthcare scenarions using benchmark image datasets (MNIST, CIFAR-10) as well as on medical images for the task of skin lesion classification. With multiple experiments, we show that even in the worst cases, combining FELICIA with real data gracefully achieves performance on par with real data while most results significantly improves the utility.

Shimaa Baraka, Benjamin Akera, Bibek Aryal et al.

Glacier mapping is key to ecological monitoring in the hkh region. Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems. In this work, we present a machine learning based approach to support ecological monitoring, with a focus on glaciers. Our approach is based on semi-automated mapping from satellite images. We utilize readily available remote sensing data to create a model to identify and outline both clean ice and debris-covered glaciers from satellite imagery. We also release data and develop a web tool that allows experts to visualize and correct model predictions, with the ultimate aim of accelerating the glacier mapping process.

Nikolay Malkin, Anthony Ortiz, Caleb Robinson et al.

We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks. We derive a new training algorithm for epitomes which allows, for the first time, learning from very large data sets and derive a label super-resolution algorithm as a statistical inference algorithm over epitomic representations. We illustrate our methods on land cover mapping and medical image analysis tasks.

Anthony Ortiz, Caleb Robinson, Dan Morris et al.

Normalization layers have been shown to improve convergence in deep neural networks, and even add useful inductive biases. In many vision applications the local spatial context of the features is important, but most common normalization schemes including Group Normalization (GN), Instance Normalization (IN), and Layer Normalization (LN) normalize over the entire spatial dimension of a feature. This can wash out important signals and degrade performance. For example, in applications that use satellite imagery, input images can be arbitrarily large; consequently, it is nonsensical to normalize over the entire area. Positional Normalization (PN), on the other hand, only normalizes over a single spatial position at a time. A natural compromise is to normalize features by local context, while also taking into account group level information. In this paper, we propose Local Context Normalization (LCN): a normalization layer where every feature is normalized based on a window around it and the filters in its group. We propose an algorithmic solution to make LCN efficient for arbitrary window sizes, even if every point in the image has a unique window. LCN outperforms its Batch Normalization (BN), GN, IN, and LN counterparts for object detection, semantic segmentation, and instance segmentation applications in several benchmark datasets, while keeping performance independent of the batch size and facilitating transfer learning.

Vincent Michalski, Vikram Voleti, Samira Ebrahimi Kahou et al.

Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.

Caleb Robinson, Anthony Ortiz, Kolya Malkin et al.

We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see the resulting effect on the model's predictions. This bi-directional feedback loop allows humans to learn how the model responds to new data. Our hypothesis is that this rich feedback allows human labelers to create mental models that enable them to better choose which biases to introduce to the model. We compare human-selected points to points selected using standard active learning methods. We further investigate how the fine-tuning methodology impacts the human labelers' performance. We implement this framework for fine-tuning high-resolution land cover segmentation models. Specifically, we fine-tune a deep neural network -- trained to segment high-resolution aerial imagery into different land cover classes in Maryland, USA -- to a new spatial area in New York, USA. The tight loop turns the algorithm and the human operator into a hybrid system that can produce land cover maps of a large area much more efficiently than the traditional workflows. Our framework has applications in geospatial machine learning settings where there is a practically limitless supply of unlabeled data, of which only a small fraction can feasibly be labeled through human efforts.

Dalton Rosario, Anthony Ortiz, Olac Fuentes

We focus on the automatic 3D terrain segmentation problem using hyperspectral shortwave IR (HS-SWIR) imagery and 3D Digital Elevation Models (DEM). The datasets were independently collected, and metadata for the HS-SWIR dataset are unavailable. We explore an overall slope of the SWIR spectrum that correlates with the presence of moisture in soil to propose a band ratio test to be used as a proxy for soil moisture content to distinguish two broad classes of objects: live vegetation from impermeable manmade surface. We show that image based localization techniques combined with the Optimal Randomized RANdom Sample Consensus (RANSAC) algorithm achieve precise spatial matches between HS-SWIR data of a portion of downtown Los Angeles (LA (USA)) and the Visible image of a geo-registered 3D DEM, covering a wider-area of LA. Our spectral-elevation rule based approach yields an overall accuracy of 97.7%, segmenting the object classes into buildings, houses, trees, grass, and roads/parking lots.

Dalton Rosario, Christoph Borel, Damon Conover et al.

Following an initiative formalized in April 2016 formally known as ARL West between the U.S. Army Research Laboratory (ARL) and University of Southern California's Institute for Creative Technologies (USC ICT), a field experiment was coordinated and executed in the summer of 2016 by ARL, USC ICT, and Headwall Photonics. The purpose was to image part of the USC main campus in Los Angeles, USA, using two portable COTS (commercial off the shelf) aerial drone solutions for data acquisition, for photogrammetry (3D reconstruction from images), and fusion of hyperspectral data with the recovered set of 3D point clouds representing the target area. The research aims for determining the viability of having a machine capable of segmenting the target area into key material classes (e.g., manmade structures, live vegetation, water) for use in multiple purposes, to include providing the user with a more accurate scene understanding and enabling the unsupervised automatic sampling of meaningful material classes from the target area for adaptive semi-supervised machine learning. In the latter, a target set library may be used for automatic machine training with data of local material classes, as an example, to increase the prediction chances of machines recognizing targets. The field experiment and associated data post processing approach to correct for reflectance, geo-rectify, recover the area's dense point clouds from images, register spectral with elevation properties of scene surfaces from the independently collected datasets, and generate the desired scene segmented maps are discussed. Lessons learned from the experience are also highlighted throughout the paper.