Impact Evaluation of Climate Smart Agriculture Program Investments in Food Security - Using Machine Learning Estimators

Q: What problem does the thesis address?

The thesis addresses vulnerability of smallholder farmers to climate events and the resulting risk to household food security.

Q: How are CSA impacts on food security estimated?

It uses a multi-country dataset with a double/debiased machine learning approach to estimate the impact of participating in a CCAFS CSA program.

Q: What does the thesis find about future food security for participants?

Combining machine learning tools with future climate data, participating households are predicted to be more likely to be food secure than non-participants across all periods, with a widening food security gap over time.

Aug 5, 2026

Upload by Quinn

Smallholder farmers in rural regions of developing countries often face high exposure to climate events, threatening agricultural yields and household food security. Climate Smart Agriculture (CSA) aims to sustain or improve production while mitigating climate change. This thesis evaluates impacts of CSA investments by the CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) using a multi-country dataset and complementary machine learning approaches, including double/debiased estimation and future climate-informed prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages95

Reading Time3 h 59 min

AccessFree to download

Abstract

Acknowledgements

Table of Contents

List of Tables

List of Figures

Introduction

Literature Related to CSA

Introduction to CSA Literature

Impact Evaluation of Climate Smart Agriculture Program Investments in Food Security Using Machine Learning Estimators by Meghan Ann Lim A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Agricultural and Resource Economics Department of Resource Economics and Environmental Sociology University of Alberta © Meghan Ann Lim, 2022 Abstract Smallholder farmers in rural regions of developing countries are often vulnerable to climate events. Climate Smart Agriculture (CSA) seeks to sustain or improve agricultural yields while mitigating climate change. The CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) has made substantial investments in developing and scaling CSA programs in developing countries. Using a multi-country dataset, this paper runs two complementary analyses. The first uses a double/debiased machine learning approach to estimate the impact of participating in a CCAFS CSA program on household food security. I estimate this impact for the entire sample and within three sub-samples, which categorize households according to their CSA adoption strategy (i.e., non-adoption, specialized adoption, or diversified adoption). Results indicate that the probability of a household being food secure is 6.0 percentage points higher (p<0.05) if it participated in a CCAFS program. The food security benefits ofCCAFS program participation are most clearly demonstrated among households that adopted a diverse set of CSA practices, where CCAFS training increased the probability of being food secure by 9.7 percentage points (p<0.05). On the other hand, the food security benefits of CCAFS training were negligible among households that did not adopt CSA practices or adopted a specialized set of practices. The second analysis combines traditional machine learning tools with future climate data to predict and compare the future food security ofCCAFS program participants and non-participants. Results show that participating households are more likely tobe food secure than non-participating households across all periods. Overall, the food security gap between participating and non-participating households is expected to increase over time. Acknowledgements I would like to thank my supervisors, Dr. Marty Luckert and Dr. Bruno Wichmann, for their support and guidance throughout my degree. Marty, thank you for taking a chance on me when Ijoined your biofuels group in 2019, and for advocating for me ever since. The growth I’ve experienced as a student and researcher wouldn’t have been possible without your leadership. Bruno, thank you for your creative genius, passion for econometric methods, and for introducing me to the fascinating world of machine learning. Lastly, thank you both for the opportunity to study a topic that aligns with my interests and future goals. I am excited for what will come next. I would also like to thank the teachers and professors who inspired me to pursue a graduate degree. I couldn’t be happier with my field of study and am honoured to be following in your footsteps. Additional thanks go to Dr. Henry An and Dr. Brent Swallow for their contributions to my thesis examination. This work was implemented as part of the CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS) led by the Alliance Biodiversity International and the International Center for Tropical Agriculture (CIAT), which is carried out with support from CGIAR Fund Donors and through bilateral funding agreements. For details, please visit [https://ccafs.cgiar.org/donors](https://ccafs.cgiar.org/donors. The views)[. The views](https://ccafs.cgiar.org/donors. The views) expressed in this document cannot be taken to reflect the official opinions of these organisations. Special thanks go to Dr. Osana Bonilla-Findji, Dr. Grazia Pacillo, and Dr. Peter Läderach for their guidance and perspective throughout this project. Additional thanks

FAQs

What problem does the thesis address?

The thesis addresses vulnerability of smallholder farmers to climate events and the resulting risk to household food security.

How are CSA impacts on food security estimated?

It uses a multi-country dataset with a double/debiased machine learning approach to estimate the impact of participating in a CCAFS CSA program.

What does the thesis find about future food security for participants?

Combining machine learning tools with future climate data, participating households are predicted to be more likely to be food secure than non-participants across all periods, with a widening food security gap over time.

Aug 5, 2026

Upload by Quinn