David B. Lobell's research while affiliated with Stanford University and other places

Publications (359)

Preprint
Full-text available
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is plentiful and the inherent temporal and multi-spectral structure provides avenues to further improve existing pre-tra...
Article
Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over large geographies can still be prohibitively expensive due to the high cost of purchasing imagery and compute....
Article
Nitrogen oxides (NOx) are among the most widely emitted pollutants in the world, yet their impacts on agriculture remain poorly known. NOx can directly damage crop cells and indirectly affect growth by promoting ozone (O3) and aerosol formation. We use satellite measures of both crop greenness and NOx during 2018-2020 to evaluate crop impacts for f...
Preprint
Full-text available
Automated tracking of urban development in areas where construction information is not available became possible with recent advancements in machine learning and remote sensing. Unfortunately, these solutions perform best on high-resolution imagery, which is expensive to acquire and infrequently available, making it difficult to scale over long tim...
Article
Full-text available
With climate change threatening agricultural productivity and global food demand increasing, it is important to better understand which farm management practices will maximize crop yields in various climatic conditions. To assess the effectiveness of agricultural practices, researchers often turn to randomized field experiments, which are reliable...
Article
Full-text available
Land cover classification in remote sensing is often faced with the challenge of limited ground truth labels. Incorporating historical ground information has the potential to significantly lower the expensive cost associated with collecting ground truth and, more importantly, enable early- and in-season mapping that is helpful to many pre-harvest d...
Article
Full-text available
In India, the second-largest sugarcane producing country in the world, accurate mapping of sugarcane land is a key to designing targeted agricultural policies. Such a map is not available, however, as it is challenging to reliably identify sugarcane areas using remote sensing due to sugarcane’s phenological characteristics, coupled with a range of...
Article
Crop management recommendations that are tailored to local conditions offer promise for improved farmer livelihoods, input use efficiency, and crop output. An important step towards achieving localized recommendations is to establish repeatable, low-cost approaches to diagnosing nutrient constraints. Satellite remote sensing is particularly attract...
Preprint
Full-text available
Crop field boundaries aid in mapping crop types, predicting yields, and delivering field-scale analytics to farmers. Recent years have seen the successful application of deep learning to delineating field boundaries in industrial agricultural systems, but field boundary datasets remain missing in smallholder systems due to (1) small fields that req...
Preprint
With climate change threatening agricultural productivity and global food demand increasing, it is important to better understand which farm management practices will maximize crop yields in various climatic conditions. To assess the effectiveness of agricultural practices, researchers often turn to randomized field experiments, which are reliable...
Preprint
Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over large geographies can still be prohibitively expensive due to the high cost of purchasing imagery and compute....
Article
Full-text available
High resolution crop type maps are an important tool for improving food security, and remote sensing is increasingly used to create such maps in regions that possess ground truth labels for model training. However, these labels are absent in many regions, and models trained in other regions on typical satellite features, such as those from optical...
Preprint
Full-text available
Index insurance is a promising tool to reduce the risk faced by farmers, but high basis risk, which arises from imperfect correlation between the index and individual farm yields, has limited its adoption to date. Basis risk arises from two fundamental sources: the intrinsic heterogeneity within an insurance zone (zonal risk), and the lack of predi...
Preprint
Full-text available
Progress toward the United Nations Sustainable Development Goals (SDGs) has been hindered by a lack of data on key environmental and socioeconomic indicators, which historically have come from ground surveys with sparse temporal and spatial coverage. Recent advances in machine learning have made it possible to utilize abundant, frequently-updated,...
Article
Climate change induced heat stress is predicted to negatively impact wheat yields across the Indo-Gangetic Plains (IGP) of India. Research suggests that early sowing of wheat can substantially reduce this impact. However, a large proportion of farmers sow wheat late across this region, likely resulting in large-scale yield loss. We examined the ext...
Preprint
Land cover classification in remote sensing is often faced with the challenge of limited ground truth labels. Incorporating historical ground information has the potential to significantly lower the expensive cost associated with collecting ground truth and, more importantly, enable early-and in-season mapping that is helpful to many pre-harvest de...
Preprint
Full-text available
High resolution crop type maps are an important tool for improving food security, and remote sensing is increasingly used to create such maps in regions that possess ground truth labels for model training. However, these labels are absent in many regions, and models trained in other regions on typical satellite features, such as those from optical...
Preprint
Full-text available
Crop type mapping at the field level is critical for a variety of applications in agricultural monitoring, and satellite imagery is becoming an increasingly abundant and useful raw input from which to create crop type maps. Still, in many regions crop type mapping with satellite data remains constrained by a scarcity of field-level crop labels for...
Article
Crop type mapping at the field level is critical for a variety of applications in agricultural monitoring, and satellite imagery is becoming an increasingly abundant and useful raw input from which to create crop type maps. Still, in many regions crop type mapping with satellite data remains constrained by a scarcity of field-level crop labels for...
Article
Full-text available
Satellite data offer great promise for improving measures related to sustainable development goals. However, assessing satellite estimates is complicated by the fact that traditional ground-based measures of these same outcomes are often very noisy, leading to underestimation of satellite performance. Here, we quantify the amount of noise in tradit...
Article
Full-text available
India relies on groundwater irrigation to produce staple grain crops that provide over half of the calories consumed by its over 1.3 billion people. While groundwater has helped India achieve grain self-sufficiency, aquifers have been overexploited across much of the country and its implications for crop production are unclear. To understand how gr...
Article
Full-text available
Crop productivity is potentially affected by several air pollutants, although these are usually studied in isolation. A significant challenge to understanding the effects of multiple pollutants in many regions is the dearth of air quality data near agricultural fields. Here we empirically estimate the effect of four key pollutants (ozone (O3), part...
Preprint
Full-text available
High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others. Unfortunately, high-resolution imagery is both infrequently collected and expensive to purchase, making it hard to efficiently and effectively scale these...
Article
Major decisions from governments and other large organizations rely on measurements of the populace's well-being, but making such measurements at a broad scale is expensive and thus infrequent in much of the developing world. We propose an inexpensive, scalable, and interpretable approach to predict key livelihood indicators from public crowd-sourc...
Article
The combination of high-resolution satellite imagery and machine learning have proven useful in many sustainability-related tasks, including poverty prediction, infrastructure measurement, and forest monitoring. However, the accuracy afforded by high-resolution imagery comes at a cost, as such imagery is extremely expensive to purchase at scale. Th...
Article
Full-text available
Remote sensing offers a way to map crop types across large spatio-temporal scales at low costs. However, mapping crop types is challenging in heterogeneous, smallholder farming systems, such as those in India, where field sizes are often smaller than the resolution of historically available imagery. In this study, we examined the potential of relat...
Article
Full-text available
Significance Monitoring compliance with environmental regulations is a global challenge. It is particularly difficult for governments in low-income countries, where informal industry is responsible for a large amount of pollution, because the governments lack the ability to locate and monitor large numbers of dispersed polluters. This study demonst...
Article
Full-text available
Agricultural research has fostered productivity growth, but the historical influence of anthropogenic climate change (ACC) on that growth has not been quantified. We develop a robust econometric model of weather effects on global agricultural total factor productivity (TFP) and combine this model with counterfactual climate scenarios to evaluate im...
Article
Satellite monitoring of development Recent years have witnessed rapid growth in satellite-based approaches to quantifying aspects of land use, especially those monitoring the outcomes of sustainable development programs. Burke et al. reviewed this recent progress with a particular focus on machine-learning approaches and artificial intelligence met...
Article
The increasing availability of satellite data at higher spatial, temporal and spectral resolutions is enabling new applications in agriculture and economic development, including agricultural insurance. Yet, effectively using satellite data in this context requires blending technical knowledge about their capabilities and limitations with an unders...
Article
Smallholder farmers face many constraints to achieving food security. Optimal soil management is often limited by a lack of accessible and accurate soil characterization, and an associated lack of soil-specific management practice recommendations. Crop yields depend on both soil quality and soil-mediated fertilizer responses. Existing research on s...
Preprint
Full-text available
Index insurance has been promoted as a promising solution for reducing agricultural risk compared to traditional farm-based insurance. By linking payouts to a regional factor instead of individual loss, index insurance reduces monitoring costs, and alleviates the problems of moral hazard and adverse selection. Despite its theoretical appeal, demand...
Preprint
Full-text available
Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to remote sensing, where unlabeled data is often abundant but labeled data is scarce. We first show that due to their different characteristics, a non-trivial gap persist...
Article
Full-text available
As climate change leads to increased frequency and severity of drought in many agricultural regions, a prominent adaptation goal is to reduce the drought sensitivity of crop yields. Yet many of the sources of average yield gains are more effective in good weather, leading to heightened drought sensitivity. Here we consider two empirical strategies...
Article
Full-text available
Crop yield maps estimated from satellite data increasingly are used to understand drivers of yield trends and variability, yet satellite-derived regional maps are rarely compared with location-specific yields due to the difficulty of acquiring sub-field ground truth data at scale. In commercial agricultural systems, combine harvesters with onboard...
Article
Full-text available
Cloud computing and freely available, high-resolution satellite data have enabled recent progress in crop yield mapping at fine scales. However, extensive validation data at a matching resolution remain uncommon or infeasible due to data availability. This has limited the ability to evaluate different yield estimation models and improve understandi...
Preprint
Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. We synthesize the growing literature that uses satellite imagery to understand these outcomes, with a focus on approaches that combine imagery with machine learning. We quantify the paucity of ground data on k...
Article
Full-text available
Field-level monitoring of crop types in the United States via the Cropland Data Layer (CDL) has played an important role in improving production forecasts and enabling large-scale study of agricultural inputs and outcomes. Although CDL offers crop type maps across the conterminous US from 2008 onward, such maps are missing in many Midwestern states...
Article
Full-text available
High resolution satellite imagery and modern machine learning methods hold the potential to fill existing data gaps in where crops are grown around the world at a sub-field level. However, high resolution crop type maps have remained challenging to create in developing regions due to a lack of ground truth labels for model development. In this work...
Article
Full-text available
Restrictions to reduce human interaction have helped to avoid greater suffering and death from the COVID-19 pandemic, but have also created socioeconomic hardship. This disruption is unprecedented in the modern era of global observing networks, pervasive sensing and large-scale tracking of human mobility and behaviour, creating a unique test bed fo...
Preprint
Full-text available
Agricultural research has fostered productivity growth, but the historical influence of anthropogenic climate change on that growth has not been quantified. We develop a robust econometric model of weather effects on global agricultural total factor productivity (TFP) and combine this model with counterfactual climate scenarios to evaluate impacts...
Conference Paper
Accurate local-level poverty measurement is an essential task for governments and humanitarian organizations to track the progress towards improving livelihoods and distribute scarce resources. Recent computer vision advances in using satellite imagery to predict poverty have shown increasing accuracy, but they do not generate features that are int...
Preprint
Full-text available
Major decisions from governments and other large organizations rely on measurements of the populace's well-being, but making such measurements at a broad scale is expensive and thus infrequent in much of the developing world. We propose an inexpensive, scalable, and interpretable approach to predict key livelihood indicators from public crowd-sourc...
Preprint
Full-text available
The combination of high-resolution satellite imagery and machine learning have proven useful in many sustainability-related tasks, including poverty prediction, infrastructure measurement, and forest monitoring. However, the accuracy afforded by high-resolution imagery comes at a cost, as such imagery is extremely expensive to purchase at scale. Th...
Article
Full-text available
Climate change is predicted to negatively impact wheat yields across northern India, primarily due to increased heat stress during grain filling at the end of the growing season. One way farmers may adapt is by sowing their wheat earlier to avoid this terminal heat stress. However, many farmers in the eastern Indo-Gangetic Plains (IGP) sow their wh...
Article
Full-text available
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectra...
Preprint
Full-text available
The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity within a single category, like as urban or vegetation, requires a large model capacity and, consequently, lar...
Preprint
Farm parcel delineation provides cadastral data that is important in developing and managing climate change policies. Specifically, farm parcel delineation informs applications in downstream governmental policies of land allocation, irrigation, fertilization, green-house gases (GHG's), etc. This data can also be useful for the agricultural insuranc...
Preprint
Full-text available
Accurate local-level poverty measurement is an essential task for governments and humanitarian organizations to track the progress towards improving livelihoods and distribute scarce resources. Recent computer vision advances in using satellite imagery to predict poverty have shown increasing accuracy, but they do not generate features that are int...
Article
The failure of early (October‐December) rains, amidst a multi‐year drought, has raised concerns of a potential emerging food security crisis in parts of southern Africa, with an estimated 45 million people at risk of severe food insecurity (WFP, 2019). Here we evaluate recent climate data to assess the possible role of anthropogenic climate change...
Article
Yield depends upon the amount of photosynthetically active radiation (PAR) absorbed by the crop during the growing season and its conversion into harvestable biomass. Little is known about attainable and actual effi-ciencies involved in absorbing incident PAR (e a) and converting it into yield (e c) in producer fields. We developed a novel approach...
Article
Full-text available
Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful t...
Article
Full-text available
The advent of multiple satellite systems capable of resolving smallholder agricultural plots raises possibilities for significant advances in measuring and understanding agricultural productivity in smallholder systems. However, since only imperfect yield data are typically available for model training and validation, assessing the accuracy of sate...
Article
Full-text available
Conservation tillage is a primary tenet of conservation agriculture aimed at restoring and maintaining soil health for long-term crop productivity. Because soil degradation typically operates on century timescales, farmer adoption is influenced by near-term yield impacts and profitability. Although numerous localized field trials have examined the...