Authors
Melissa Morgan
News Type
Blogs
Date
Paragraphs

Autumn has arrived at Stanford, and so has a new cohort of students to the Ford Dorsey Master's in International Policy (MIP) program.

MIP is a two-year graduate program administered by the Freeman Spogli Institute for International Studies (FSI) at Encina Hall. While it is structured broadly into four areas of specialization—Cyber Policy and Security (CYBER); Energy, Natural Resources, and the Environment (ENRE); Governance and Development (GOVDEV); and International Security (ISEC)—students are encouraged to personalize their learning according to their interests and goals and engage with scholars from across Stanford's campus. At the end of their studies, students participate in the Policy Change Studio, a unique capstone project designed to give them practical experience with policymaking through in-the-field research and direct collaboration on projects with partner organizations all over the world.

This highly interdisciplinary, hands-on approach to learning is one of the major appeals of the MIP program, which draws applicants from all over the world. This year, the program is welcoming 22 students from thirteen countries and regions, including Haiti, Hong Kong S.A.R., India, Indonesia, Japan, Kenya, Lebanon, Russia, Rwanda, South Korea, Thailand, the United Kingdom, and the United States. They bring to MIP insights from prior experience in academia, military training, and assignments as diplomats and civil servants.

Keep reading to meet six of our new students and learn more about their stories, their goals for the future, and what has them excited to be studying at the MIP program.
 


Halkano Boru, studying International Security (ISEC); From: Nairobi, Kenya; Fun Facts: Soccer fan, burgeoning beach volleyball player, and tennis-curious
Halkano Boru

I am coming into the MIP program from the world of foreign and defense analysis. I’ve had the opportunity to work for various groups in and out of the government in Washington D.C. looking at the foreign policy and defense strategy of various parts of Africa, the Gulf, and how the U.S. interacts with these regions.

I am particularly interested in a range of complex policy areas focusing on peace and security. My interests include evolving dynamics of drone warfare by great powers and middle powers, use of paramilitary groups by states, and strategies for countering political violence in authoritarian regimes.  

That technology aspect is one reason that drew me here to Stanford and its proximity to the Silicon Valley ecosystem. And, of course, there’s the AI aspect as well. “AI” is the buzzword in everything right now, but I want to know how these new tools and technologies are shaping political violence, democracies, and the global governance structure as a whole. If we don’t understand where the violence is coming from, we can’t understand how to pursue strategies for peace.

Another big appeal of the MIP program was that it allows me to interact with scholars like Francis Fukuyama, Larry Diamond, James Fearon, and Joe Felter. These are names I’ve read and referenced in my analytic work, and now I have the opportunity to learn from them directly. And who knows; maybe I will come back someday as a colleague if I return to Stanford for my PhD! With the hands-on experience at MIP, the networking opportunities here, and the emphasis on both quantitative and qualitative learning, I know I’m going to be in a good position to meet my goals and make a difference.
 


 

Christina Farhat, studying Cyber Policy & Security (CYBER); From: Beirut, Lebanon; Fun Facts:  E-waste entrepreneur who went viral on social media for a GPU purse
Christina Farhat

If you had told me ten years ago that I would be working on artificial intelligence at Stanford, in the heart of Silicon Valley, I wouldn’t have believed you. When applying to undergrad, I had to submit my application from an internet cafe in Beirut because the internet in my village in Lebanon wasn’t fast enough to upload my application. To go from a small village in Lebanon to studying at Stanford is a dream come true.

The path that led me here isn’t straightforward, but the thread that connects my experiences is a desire to be a voice for people who aren’t in the room. When I was a foreign correspondent, I published stories about systemic inequities and disadvantages. At the World Bank, it was pointing out biases and gaps in the data sets that directly impacted the distribution of aid and personal protective equipment. Today we are told artificial intelligence is going to be a “democratizing” technology. What about people who don’t have electricity? Who don’t have $20 for a ChatGPT subscription? Who have no AI literacy?  

If AI is going to impact every single person on earth’s life, how we build it can’t be decided by 0.01% of the population. If this is a printing press, Gutenberg Bible moment in history, we can’t simply leave entire communities, entire countries, nor entire continents out of the conversation. 

Drafting better AI policy is why I came back to school to the MIP program at Stanford. I worked with engineers who were Stanford CS alumni, and they were always so collaborative and inclusive. They patiently answered all of my questions while training an LLM. Those are the kinds of people and the kinds of values I want to work with to tackle these challenges. I’ve already seen that spirit here in the few weeks I’ve been at Stanford. These values of connecting the dots between engineering, policy, law and other disciplines has given me confidence that working together, we can write better AI policy and improve outcomes well beyond Silicon Valley. 
 


 

Gil Jospeh, studying Governance and Development (GOVDEV); From: Port-au-Prince, Haiti; Fun Facts: Spaghetti aficionado and cycling enthusiast
Gil Jospeh

I come from Haiti, which is a small country. As such, we don’t always think about our foreign policy in an integrated way. How are our population, demography, topography, and borders linked? What about our trade partners and migration patterns? How do those impact our relationships with neighboring countries, or places with diaspora communities like the U.S.? I studied some of these questions while I was an undergrad at Princeton, but there’s much more to understand. 

My dream job is to work in the Ministry of Foreign Affairs in Haiti. So while I’m here at Stanford, I’m trying to write a handbook of sorts for myself and build out the agenda I hope to have someday. That is what is giving me direction for my time here at Stanford. If I’m learning about the balance of payments, the question I’m asking myself is, “What is Haiti’s balance of payment? What does it look like? What are the policy implications of that?”

By the time I graduate, I want to have a fully drafted idea of where Haiti’s policy landscape is currently, so I know what priorities to set to work on for the future. The fact that the MIP program is so customizable is one of the big reasons I wanted to come here; I can really tailor my studies to support these bigger projects. I get to make this time what I want it to be, and what will be most helpful to my goals.

But I also want to challenge myself to think beyond my field and learn about other parts of the world that may not have anything in common with Haiti, at least on the surface. I want to have a local impact, but I also want to develop as a global thinker. There’s a lot that connects us beyond our borders, and being able to think about those connections in a systematic, global way will only become more and more important as populations continue to migrate and integrate into communities throughout the world.
 


 

Paulina Montgomery, studying International Security (ISEC); From: Los Angeles, California, U.S.A.; Fun Facts:  Avid equestrian, aggressively mediocre skier, and lifelong dinosaur lover
Paulina Montgomery

When I was serving as an active duty Space Operations Army officer, I had the opportunity to work on electromagnetic warfare and space control operations around the globe. My background is originally in history, and I began my military career as a military police officer, but I’ve always been really passionate about being part of the future.

There’s so much incredible defense technology out there, but the most up-to-date and effective versions don’t always get down to the individuals who really need them to operate effectively. There are so many inefficiencies and gaps between what’s actually codified in policy and what the warfighters on the ground need to execute their missions.

And that’s true of large-scale policies as well. Take the Space Treaty, for example. It was written back in 1967 when there were just 24 known satellites in orbit. Now there are thousands of satellites in orbit, yet we don't have another foundational governing document around space protocols. That’s got to change.

That’s what I want to start tackling while I’m here at Stanford. Making systemic changes in big organizations like the Department of Defense isn’t going to be easy, but we’ve got to close those knowledge gaps between the policymakers, the high level leaders and stakeholders, and those who are actually pressing the buttons of our space systems. We can't avoid these issues anymore, because it’s not just about the military or defense: it’s ATMs, it’s GPS, it's traffic lights, it's everything. There are no borders in space, so we must work hand-in-hand with our partners and allies to be successful in this emerging domain. This problem set truly involves everyone.

This is why being here at Stanford is going to be so beneficial. In addition to my courses in policy, it’s so easy to take a law or a business class or sit in on an aeronautics course. And we’re right in Silicon Valley where a lot of this technology is being built and distributed. That makes it so easy to look at these issues from different perspectives and get new insights into how to tackle them. We need a well-rounded perspective in order to get the right knowledge to the right people to make the right decisions.
 


 

Boss Pornprasert, studying International Security (ISEC); From: Samut Songkhram, Thailand; Fun Facts:  Master Thai pad krapao maker and traditional Japanese flutist
Boss Pornprasert

At the root of all my interests in policy and foreign affairs is a desire to help people. I’ve always been drawn to problems that involve alleviating difficulties, whether that’s humanitarian issues, conflict resolution, or any other issues where civilians are not fairly represented. When I was first considering working in government, it was the consular aspect—being able to serve people from Thailand all over the world— that really appealed to me.

When I had the opportunity to serve at the UN as a Peace and Security Intern at the Permanent Mission of Thailand, my excitement for that assignment came from the same place; I liked the spirit of people coming together to discuss problems. There’s been waning faith about the usefulness of these types of big, multilateral organizations, but I still believe these kinds of bodies are important forums for dealing with conflicts. Reforms are needed, yes, but we can’t simply sideline conversations that are difficult to have or shut out nations we don’t easily agree with.

My own country of Thailand, for example, is not the biggest or most influential nation on security issues, but we have a lot we can teach and discuss when it comes to development. How do we balance some of that influence? How do we give countries in the global south more representation on these stages? Or domestically, how can we create policies that actually make a difference to people for the better? There tends to be a lot of talk and lofty goals, but then little action or follow through. 

That’s why one of the major appeals of coming to the MIP program was the emphasis on studying policymaking frameworks. In my undergrad at Columbia, I studied a lot of political theory and philosophy through the core curriculum. Here at Stanford, I want my focus to be on framing, implementation, and learning how to do things that address issues, not just identify them. I will be entering the Thai Foreign Service when I’m finished with my schooling, and I want to be as prepared as possible to excel as a diplomat—someone capable of solving problems effectively as part of a team, and, above all, helping people. I’m excited to learn from the experiences and perspectives of my cohort. MIP may not be as big as the UN, but we’re our own multilateral, multinational group trying to make a difference.
 


 

Mariko Takatani, studying Energy, Natural Resources, & the Environment (ENRE); From: Tokyo, Japan; Fun Facts: Former ballerina and windsurfer, and newly aspiring golfer
Mariko Takatani

Behind all of my interests and experiences in policy is a commitment to understand how we shape and are shaped by the environment. Living  in different places and engaging with many kinds of people in different cultures has shown me how our lives are deeply connected to the environments we inhabit. No matter where we come from, we all depend on the same planet. We all have a stake in sustaining this place we share.

That being said, as a former negotiator for the Ministry of Economy, Trade, and Industry (METI) in Japan, I know that the best course of action for how to protect the environment is not always easy or straightforward. Climate policies that make sense in one place may not be feasible in another. Requirements about renewables that work here may not work elsewhere. There are some things that we can do universally, but it’s also important that countries realize and respect that each nation has different circumstances that will require unique planning and policies to address.

One of the areas in which I would specifically like to develop is finding ways to incentivize trade policies that accelerate the dissemination of clean, low emission, or zero emission technologies. How can we make climate-related goods more appealing to the global market? How can we get over price barriers and lower the cost of climate-related products? I want to live in a world where products and trade that support climate goals are the norm, not a specialty, and those goods are easy for everyone to access.

I’ve been fortunate to have experiences already in international engagement and inter-government coordination on climate and trade negotiations, but I am looking forward to being able to learn much more about the science side of climate and the environment. Having the ability to combine my MIP classes with courses from the Doerr School of Sustainability was one of the big appeals for me in coming to this program. Gaining that dual background in policy and analytical skills from MIP and science and research from Doerr through my electives is going to be incredibly beneficial to bring back to my ministry.
 


 

Read More

The Class of 2026 of the Ford Dorsey Master's in International Policy on the steps of Encina Hall at Stanford University.
News

Meet the Ford Dorsey Master's in International Policy Class of 2026

Hailing from every corner of the globe, the new class of the Ford Dorsey Master's in International Policy is ready to make an impact on nuclear policy, digital trust and safety, rural investment, and more.
Meet the Ford Dorsey Master's in International Policy Class of 2026
Photo of MIP Student RJ Teoh posing with two others in front of a banner that reads 2025 Exercise Cyber Star
Blogs

Bridging Policy and Practice: My Summer with SANS Singapore

Bridging Policy and Practice: My Summer with SANS Singapore
The graduating class of 2025 of the Ford Dorsey Master's in International Policy on the steps of Encina Hall at Stanford University.
News

“It Is Your Job to Make the Plan:” MIP Graduates Given a Charge to Serve as Leaders and Take Action with Empathy

In his remarks to the Class of 2025 of the Ford Dorsey Master’s in International Policy, Lieutenant General H.R. McMaster (Ret.) called for the new graduates to lead with confidence.
“It Is Your Job to Make the Plan:” MIP Graduates Given a Charge to Serve as Leaders and Take Action with Empathy
Hero Image
The 2027 cohort of the Ford Dorsey Master's in International Policy. Rod Searcey
All News button
1
Subtitle

Twenty-two students from around the world have landed at Stanford ready to take on pressing issues in international security, space defense, environmental policy, and multilateral reforms.

Date Label
Paragraphs

Supply chains can be surprisingly complex. In many low- and middle-income settings, large companies often rely on networks of small, independent distributors who travel by foot to sell consumer goods to otherwise hard-to-reach customers (Kruijff et al. 2024). These ‘micro-distributors’ operate at the far edge of the supply chain, with no formal employment contracts, thin profit margins, and high levels of economic risk.

In a field experiment in Kenya, we partnered with one of the world’s largest food manufacturers (pseudonymously “FoodCo”) to evaluate whether investment-appropriate financing contracts could help their independent distributors improve their business performance. We found that tailoring repayment terms to better share risk and rewards—compared to a standard, rigid debt contract—significantly boosted distributors’ profits. Crucially, these more flexible contracts took advantage of detailed administrative data on monthly performance. These findings underscore the promise of improved observability enabled by digitisation: with richer data, financial contracts can be designed to incorporate greater risk-sharing (Fischer 2013, Meki 2024), potentially opening new opportunities for mutually beneficial investments.

All Publications button
1
Publication Type
Journal Articles
Publication Date
Subtitle

Flexible financing for ‘last-mile’ distributors boosted profits across a food supply chain in Kenya.

Journal Publisher
VoxDev
Authors
Marcel Fafchamps
Authors
Rachel Owens
News Type
News
Date
Paragraphs

In a CDDRL seminar series talk, Daniel Chen — Director of Research at the French National Center for Scientific Research and Professor at the Toulouse School of Economics — examined whether data science can improve the functioning of courts and unlock their impact on economic development. Improving courts’ efficiency is paramount to citizens' confidence in legal institutions and proceedings.

In a nationwide experiment in Kenya, Chen and his co-authors employed data science techniques to identify the causes of case backlog in the judicial system. They developed an algorithm to identify major sources of court delays for each of Kenya’s 124 court stations. Based on the algorithm, they compiled a one-page report — specific to the local court and tailored to that month’s proceedings — which provided an analysis of court adjournments, reasons for delay, and tangible action items.

To measure the effect of these one-pagers, Chen established two treatment groups and one control. Those in the first treatment group received a singular one-pager, sent just to the courts. The second received one for the courts and one for a Court User Committee (CUC). The committee, which consists of lawyers, police, and members of civil society, was asked to discuss the one-pagers during their quarterly meetings. 

To measure the relevant effects, the authors examined three primary outcomes, namely: (1) adjournment (or case delay) rates; (2) quality and citizen satisfaction; and (3) measures of economic development, including contracting, investment, and business creation. 

Results showed the intervention was associated with a 22 percent improvement in adjournments, or a decline in trial length by 120 days. They found that there was no effect on either the number of cases filed or the proxies for quality. Citizen satisfaction rates also went up, with a reduction in complaints about speed and quality, and the intervention was associated with an increase in formal written contracts and higher wages.

Read More

María Ignacia Curiel presents during CDDRL's research seminar
News

Do Institutional Safeguards Undermine Rebel Parties?

CDDRL postdoctoral fellow’s findings show that institutional safeguards meant to guarantee the representation of parties formed by former rebel groups may actually weaken such parties’ grassroots support.
Do Institutional Safeguards Undermine Rebel Parties?
Larry Diamond speaks during CDDRL's research seminar
News

Is the World Still in a Democratic Recession?

Is the world still in a democratic recession? Larry Diamond — the Mosbacher Senior Fellow in Global Democracy at FSI — believes it is.
Is the World Still in a Democratic Recession?
Janka Deli presents during CDDRL seminar
News

Can Markets Save the Rule of Law?: Insights from the EU

CDDRL postdoctoral fellow challenges the conventional wisdom that deterioration in the rule of law generates decline in economic vitality.
Can Markets Save the Rule of Law?: Insights from the EU
Hero Image
Daniel Chen
Daniel Chen presents in CDDRL's research seminar on November 9, 2023.
Rachel Cody Owens
All News button
1
Subtitle

Improving courts’ efficiency is paramount to citizens' confidence in legal institutions and proceedings, explains Daniel Chen, Director of Research at the French National Center for Scientific Research and Professor at the Toulouse School of Economics.

Date Label
Authors
Melissa Morgan
Mi Jin RYU
News Type
Blogs
Date
Paragraphs

For forty years, the Ford Dorsey Master's in International Policy program has offered students a unique approach to studying policy and the complex challenges of an ever more connected global community. No where does the combination of theory, practical application, and hands-on learning come together more clearly than the annual Policy Change Studio, the capstone experience of second-year MIP students. 

The two-quarter course allows MIP students to put their classroom learning into practice by partnering with organizations actively working on global policy problems. Working in coordination with local organizations, students analyze specific policy problems, craft solutions, and develop implementation plans alongside stakeholders in communities around the world.

This year, our students criss-crossed the globe from England to Egypt, the Maldives to Switzerland, Japan and Vietnam, Kenya, Ghana, Fiji, and beyond to meet with their organizations and hone their policy plans. Keep reading to learn more.
 

Ghana

Arden Farr, Corinna Ha, and Munashe Mataranyika have been in Ghana working with the Centre for Democratic Development - Ghana (CDD - Ghana) on a project aimed at developing parity and addressing barriers to women's representation in local government.

Egypt and England

Luis Sanchez, Taimur Ahmad, Jasdeep Singh Hundal, and Shiro Wachira visited Cairo, Egypt and London, England to work with the European Bank for Reconstruction and Development (EBRD) to better understand the barriers small and medium-sized enterprises face in making contributions toward food security in Egypt. While in Cairo, the team attended various regional conferences and met with entrepreneurs, investors and experts working in the African innovation ecosystem.

Japan and Vietnam

Omar Pimentel, Jonathan Deemer, Miku Yamada, and Mi Jin Ryu, partnered with the Lawrence Livermore National Laboratory (LLNL), traveled to Tokyo, Japan and Hanoi, Vietnam to research the implications of China’s plan to deploy floating nuclear power plants in the South China Sea.

Europe

Angela Chen, Brian Slamkowski, and Francesca Bentley travelled to Europe to partner with the North Atlantic Treaty Organization (NATO)'s Innovation Unit, working together to determine strategies to promote responsible biotechnology innovation while reducing its potential for misuse.

Kenya

Ben Zehr, Chubing Li, Joyce Lin and Kyle Smith traveled to Homa Bay and Isebania in Western Kenya to better understand Nuru Kenya’s efforts in supporting farmers’ cooperatives to build sustainable horticultural and dairy agribusinesses while practicing more conscientious water resource management.

Fiji

Ilari Papa, Daniel Donghun Kim, Caroline Meinhardt, and Tanvi Gupta visited Fiji to work with the Oceania Cyber Security Centre (OCSC) to identify the root causes of online misinformation in the country and brainstorm solutions to counter them.

The Maldives and Switzerland

Ben Zuercher, Dulguun Batmunkh, and Suman Kumar traveled to the Maldives and Switzerland and met with local government agencies, NGOs, and private sector representatives to learn more about domestic and international challenges to financing climate change adaptation and mitigation. Anna Kumar traveled to New York and Washington, D.C. to participate in a UN conference and hear from representatives of multilateral organizations, different countries, and leading climate finance start-ups about the progress being made on the goals set out in the Paris Climate Agreement.

The Ford Dorsey Master's in International Policy

Want to learn more? MIP holds admission events throughout the year, including graduate fairs and webinars, where you can meet our staff and ask questions about the program.

Read More

Francis Fukuyama instructs students from the 2023 cohort of the Ford Dorsey Master's in International Policy in the Policy Impact Lab.
News

The 2023 MIP Cohort Gears Up For Their Policy Impact Projects

The 2023 cohort of the Ford Dorsey Master's in International Policy are spreading out across the globe to practice their policymaking skills on issues such as women’s political representation in Ghana and food insecurity in Egypt.
The 2023 MIP Cohort Gears Up For Their Policy Impact Projects
Luis Sanchez at the Summit for the Future of Central America
Blogs

Bringing the Green Revolution to El Salvador

Over the summer of 2022, Luis Sanchez worked in the Executive Office of the President Nayib Bukele and Vice President Felix Ulloa of El Salvador.
Bringing the Green Revolution to El Salvador
The Ford Dorsey Master's in International Policy Class of 2024 at the Freeman Spogli Institute for International Studies.
Blogs

Meet the Ford Dorsey Master's in International Policy Class of 2024

The 2024 class of the Ford Dorsey Master’s in International Policy has arrived at Stanford eager to learn from our scholars and tackle policy challenges ranging from food security to cryptocurrency privacy.
Meet the Ford Dorsey Master's in International Policy Class of 2024
Hero Image
A photo collage of the 2023 cohort of the Ford Dorsey Master's in International Policy on their Policy Change Studio internships.
Students from the 2023 cohort of the Ford Dorsey Master's in International Policy traveled all over the world to work with organizations on local policy projects.
Ford Dorsey Master's in International Policy
All News button
1
Subtitle

From Egypt to England, the Maldives to Switzerland, Vietnam, Ghana, Kenya, and Fiji, the 2023 cohort of the Ford Dorsey Master's in International Policy has criss-crossed the world practicing their policymaking skills.

Paragraphs

People’s value for their own time is a key input in evaluating public policies: evaluations should account for time taken away from work or leisure as a result of policy. Using rich choice data collected from farming households in western Kenya, we show that households exhibit nontransitive preferences consistent with behavioral features such as loss aversion and self-serving bias. As a result, neither market wages nor standard valuation techniques (such as the BeckerDeGroot-Marschak—BDM—mechanism of Becker et al., 1964) correctly measure participants’ value of time. Using a structural model, we identify the mix of behavioral features driving our choice data. We find that these features distort choices when exchanging cash either for time or for goods. Our model estimates suggest that valuing the time of the self-employed at 60% of the market wage is a reasonable rule of thumb.

All Publications button
1
Publication Type
Working Papers
Publication Date
Subtitle

Pascaline Dupas and co-authors Agness, Baseler, Chassang, and Snowberg leverage individual choice data they generate on farmers in western Kenya to solve a general problem: do behavioral phenomena drive individual choices when trading off cash for time, or cash and time for goods?

Authors
All Publications button
1
Publication Type
Journal Articles
Publication Date
Subtitle
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 training supervised classification models. When training data is not available in one region, classifiers trained in similar regions can be transferred, but shifts in the distribution of crop types as well as transformations of the features between regions lead to reduced classification accuracy. We present a methodology that uses aggregate-level crop statistics to correct the classifier by accounting for these two types of shifts. To adjust for shifts in the crop type composition we present a scheme for properly reweighting the posterior probabilities of each class that are output by the classifier. To adjust for shifts in features we propose a method to estimate and remove linear shifts in the mean feature vector. We demonstrate that this methodology leads to substantial improvements in overall classification accuracy when using Linear Discriminant Analysis (LDA) to map crop types in Occitanie, France and in Western Province, Kenya. When using LDA as our base classifier, we found that in France our methodology led to percent reductions in misclassifications ranging from 2.8% to 42.2% (mean = 21.9%) over eleven different training departments, and in Kenya the percent reductions in misclassification were 6.6%, 28.4%, and 42.7% for three training regions. While our methodology was statistically motivated by the LDA classifier, it can be applied to any type of classifier. As an example, we demonstrate its successful application to improve a Random Forest classifier.
Journal Publisher
Remote Sensing of Environment
Authors
David Lobell
Paragraphs

Accurate measurements of maize yields at field or subfield scales are useful for guiding agronomic practices and investments and policies for improving food security. Data on smallholder maize systems are currently sparse, but satellite remote sensing offers promise for accelerating learning about these systems. Here we document the use of Google Earth Engine (GEE) to build “wall-to-wall” 10 m resolution maps of (i) cropland presence, (ii) maize presence, and (iii) maize yields for the main 2017 maize season in Kenya and Tanzania. Mapping these outcomes at this scale is extremely challenging because of very heterogeneous landscapes, lack of cloud-free satellite imagery, and the low quantity of quality ground-based data in these regions.

First, we computed seasonal median composites of Sentinel-1 radar backscatter and Sentinel-2 optical reflectance measures for each pixel in the region, and used them to build both crop/non-crop and maize/non-maize Random Forest (RF) classifiers. Several thousand crop/non-crop labels were collected through an in-house GEE labeler, and thousands of crop type labels from the 2015–2017 growing seasons were obtained from various sources. Results show that the crop/non-crop classifier successfully identified cropland with over 85% out-of-sample accuracy in both countries, with Sentinel-1 being particularly useful for prediction. Among the cropped pixels, the maize/non-maize classier had an accuracy of 79% in Tanzania and 63% in Kenya.

To map maize yields, we build on past work using a scalable crop yield mapper (SCYM) that utilizes simulations from a crop model to train a regression that predicts yields from observations. Here we advance past approaches by (i) grouping simulations by Global Agro-Environmental Stratification (GAES) zones across the two countries, in order to account for landscape heterogeneity, (ii) utilizing gridded datasets on soil and sowing and harvest dates to setup model simulations in a scalable way; and (iii) utilizing all available satellite observations during the growing season in a parsimonious way by using harmonic regression fits implemented in GEE. SCYM estimates were able to capture about 50% of the variation in the yields at the district level in Western Kenya as measured by objective ground-based crop cuts.

Finally, we illustrated the utility of our yield maps with two case studies. First, we document the magnitude and interannual variability of spatial heterogeneity of yields in each district, and how it varies for different parts of the region. Second, we combine our estimates with recently released soil databases in the region to investigate the most important soil constraints in the region. Soil factors explain a high fraction (72%) of variation in predicted yields, with the predominant factor being soil nitrogen levels. Overall, this study illustrates the power of combining Sentinel-1 and Sentinel-2 imagery, the GEE platform, and advanced classification and yield mapping algorithms to advance understanding of smallholder agricultural systems.

All Publications button
1
Publication Type
Journal Articles
Publication Date
Journal Publisher
Remote Sensing of Environment
Authors
George Azzari
Stefania Di Tommaso
David Lobell
0
CDDRL Postdoctoral Scholar, 2020-21
thumbnail_leah1_small.jpg

My research centers on topics in comparative politics and the political economy of development. I focus on the micro-foundations of political behavior to gain leverage on macro-political questions. How do autocrats survive? How can citizen-state relations be improved and government accountability strengthened? Can shared identities mitigate out-group animosity? Adopting a multi-method approach, I use lab-in-the-field and online experiments, surveys, and in-depth field research to examine these questions in sub-Saharan Africa and the US. My current book project reexamines the role of elections in authoritarian endurance and explains why citizens vote in elections with foregone conclusions in Tanzania and Uganda. Moving beyond conventional paradigms, my theory describes how a social norm of voting and accompanying social sanctions from peers contribute to high turnout in semi-authoritarian elections. In other ongoing projects, I study how national and pan-African identification stimulated through national sports games influence attitudes toward refugees, the relationship between identity, emotions, and belief in fake news, and how researchers can use Facebook as a tool for social science research.

Paragraphs

Large and regular seasonal price fluctuations in local grain markets appear to offer African farmers substantial inter-temporal arbitrage opportunities, but these opportunities remain largely unexploited: small-scale farmers are commonly observed to "sell low and buy high" rather than the reverse. In a field experiment in Kenya, we show that credit market imperfections limit farmers' abilities to move grain inter-temporally. Providing timely access to credit allows farmers to buy at lower prices and sell at higher prices, increasing farm revenues and generating a return on investment of 28%. To understand general equilibrium effects of these changes in behavior, we vary the density of loan offers across locations. We document significant effects of the credit intervention on seasonal price fluctuations in local grain markets, and show that these GE effects shape individual level profitability estimates. In contrast to existing experimental work, the results indicate a setting in which microcredit can improve firm profitability, and suggest that GE effects can substantially shape microcredit's effectiveness. In particular, failure to consider these GE effects could lead to underestimates of the social welfare benefits of microcredit interventions.

All Publications button
1
Publication Type
Working Papers
Publication Date
Journal Publisher
NATIONAL BUREAU OF ECONOMIC RESEARCH
Authors
Paragraphs

Accurate measurements of crop production in smallholder farming systems are critical to the understanding of yield constraints and, thus, setting the appropriate agronomic investments and policies for improving food security and reducing poverty. Nevertheless, mapping the yields of smallholder farms is challenging because of factors such as small field sizes and heterogeneous landscapes. Recent advances in fine-resolution satellite sensors offer promise for monitoring and characterizing the production of smallholder farms. In this study, we investigated the utility of different sensors, including the commercial Skysat and RapidEye satellites and the publicly accessible Sentinel-2, for tracking smallholder maize yield variation throughout a ~40,000 km2western Kenya region. We tested the potential of two types of multiple regression models for predicting yield: (i) a “calibrated model”, which required ground-measured yield and weather data for calibration, and (ii) an “uncalibrated model”, which used a process-based crop model to generate daily vegetation index and end-of-season biomass and/or yield as pseudo training samples. Model performance was evaluated at the field, division, and district scales using a combination of farmer surveys and crop cuts across thousands of smallholder plots in western Kenya. Results show that the “calibrated” approach captured a significant fraction (R2 between 0.3 and 0.6) of yield variations at aggregated administrative units (e.g., districts and divisions), while the “uncalibrated” approach performed only slightly worse. For both approaches, we found that predictions using the MERIS Terrestrial Chlorophyll Index (MTCI), which included the red edge band available in RapidEye and Sentinel-2, were superior to those made using other commonly used vegetation indices. We also found that multiple refinements to the crop simulation procedures led to improvements in the “uncalibrated” approach. We identified the prevalence of small field sizes, intercropping management, and cloudy satellite images as major challenges to improve the model performance. Overall, this study suggested that high-resolution satellite imagery can be used to map yields of smallholder farming systems, and the methodology presented in this study could serve as a good foundation for other smallholder farming systems in the world.

All Publications button
1
Publication Type
Journal Articles
Publication Date
Journal Publisher
Remote Sensing
Authors
George Azzari
David Lobell
Subscribe to Kenya