Agriculture in a Changing Climate - Applications of Machine Learning and Remote Sensing for Measurement and Adaptation - Doctor of Philosophy Dissertation

Aug 5, 2026

Upload by Aria

This dissertation examines how large-scale datasets and modern machine learning methods can address climate and sustainability challenges in agriculture. It focuses on translating complex data into accurate, actionable information and determining when that information yields real insight into key problems. Across three chapters, it validates satellite-driven estimates of planting and harvest dates, models crop yields from daily weather with deep learning and interpretable analysis, and tests field-level monitoring methods for smallholder farms in Kenya.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages155

Reading Time6 h 31 min

AccessFree to download

Acknowledgments

Dedication

Chapter 1: Documenting climate impacts and adaptation with a remotely sensed dataset of US corn planting and harvest dates

1.1 Introduction

1.1.1 Related literature

1.2 Data

1.2.1 Geographic and temporal samples

1.2.2 Crop progress

Agriculture in a Changing Climate: Applications of Machine Learning and Remote Sensing for Measurement and Adaptation Isabella Smythe Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy under the Executive Committee of the Graduate School of Arts and Sciences COLUMBIA UNIVERSITY © 2024 Isabella Smythe All Rights Reserved Abstract Agriculture in a Changing Climate: Applications of Machine Learning and Remote Sensing for Measurement and Adaptation Isabella Smythe This work considers how large-scale datasets and novel machine learning methods can be applied to challenges in climate and sustainability, with a particular focus on agriculture. Effectively leveraging these advancements for sustainable development research requires answering two questions: first, how can complex data be translated into useful and accurate information? And second, under what circumstances does this information offer real insight into an important problem? In answer to the second of these questions, the research in the three chapters of this dissertation falls broadly into one of two categories: problems for which high spatial-or temporal-resolution data is necessary but infeasible to collect at scale (Chapters 1 and 3); and problems for which the structure of relationships between features and outcomes is complex, with important non-linearities, interactions, or other nuances that may be overlooked by traditional approaches (Chapters 1 and 2) . Both such categories of problem are common in the domain of agriculture, an industry which is critical for food security and economic well-being, but highly susceptible to fluctuations in weather and climate. In Chapter 1, I introduce and validate a method for creating high-resolution estimates of planting and harvest dates for United States crops with satellite imagery. This data is an important input for many research applications, but is only tracked at the state level. The resulting dataset is then used to generate more accurate measures of the weather conditions crops are exposed to during their growing season, and thus more precise estimates of how these conditions impact yields. These estimates suggest a 17% larger impact of extreme heat (> 29◦ C) on crop yields than previously documented, with substantial variation in heat sensitivity over the course of the growing season. However, the overall impact of increased temperatures is partially offset by a reduced estimate of growing season duration and a 276% increase in the estimated benefits of warm (10-29◦ C) temperatures. Finally, I present novel evidence that farmers use early planting as a form of adaptation to warming, with planting dates shifting earlier by 0.13 days for each additional 30◦ C day during the growing season. Chapter 2 presents an even more flexible formulation for estimating US crop yields. I introduce a deep learning model that predicts yields directly from daily weather data, and show that it reduces out-of-sample error by 10.7% relative to standard linear modeling approaches. Using interpretable machine learning techniques, I demonstrate that this model learns a number of nuanced patterns consistent with expectations from agronomic theory, including spatial and geographic variation, interactions between weather features, and nonlinearity over weather feature values. Over several simulations, these models estimate future impacts of warming that are two to three times less severe than prior modeling approaches would suggest. However, the complexities of causal identification with highly flexible models mean that these results must be interpreted with caution; primarily, they suggest that estimates of climate impacts may be highly sensitive to feature selection, and to precise trends in warming over the course of the growing season. Finally, Chapter 3 turns to smallholder farms in Kenya, as part of research done with support from Atlas AI. A collection of appr

FAQs

What central problem does the dissertation address for agriculture under climate change?

It evaluates how machine learning and remote sensing can convert large, complex datasets into accurate information that meaningfully supports measurement of climate impacts and adaptation strategies.

How does Chapter 1 estimate climate exposure for US crops?

It validates a satellite-imagery method to generate high-resolution estimates of planting and harvest dates, then uses these to compute more precise weather conditions during the growing season and their effects on yields.

What modeling approach is presented in Chapter 2 for US crop yields?

It introduces a deep learning model that predicts yields directly from daily weather data, and uses interpretable machine learning to reveal nuanced non-linear patterns while noting that causal interpretation can be sensitive to feature selection and warming trends.

Aug 5, 2026

Upload by Aria