Stanford University

Agriculture

Hands on Policy Practice: A Look at the MIP Capstone Projects of 2024

Authors
News Type
News
Date
Paragraphs

Spring is just around the corner at the Farm, which means it's time for the students in the 2024 cohort of the Ford Dorsey Master's in International Policy program (MIP) to put down the books, roll up their sleeves, and get to work on their capstone projects.

Each year, second-year MIP students participate in the Policy Change Studio, an innovative two-quarter course that is designed to provide students with the know-how to bring about change in the world through hands-on projects. After a year and a half of studying the principles and frameworks of effective policymaking, our students take those ideas out of the classroom and put them into practice in projects sponsored by research groups, NGOs, and policy institutions all over the world.

This year our students are criss-crossing the globe to work on AI governance in Brazil, transportation systems in Ghana, sustainable agriculture in Mongolia, and much more. Keep reading to learn more about each project.

 

Digital Resilience for Conflict Scenarios in Taiwan

We are working with the National Taiwan Ocean University and the Taiwan Law and Technology Association led by Dr. Yachi Chiang (江雅綺) to help strengthen the security and integrity of Taiwan’s undersea cables. Specifically, our focus is on cable resiliency against PRC aggression, given that
Ford Dorsey Master's in International Policy students Dwight Knightly, Hamzah Daud, Tabatha Anderson, and Francesca Verville.
Dwight Knightly, Hamzah Daud, Francesca Verville, and Tabatha Anderson

the Taiwanese cables to the Matsu Islands have been cut 27 times, most recently in spring 2023. Our final report and presentation will analyze Taiwan’s current emergency management and resiliency plans, identify areas of improvement, and present solutions to fix these gaps. All of us care deeply about democracy and the rule of law, and the security of Taiwan against PRC aggression is central in the fight for those ideals. Our hope is that this work helps in some small way to improve the security of Taiwan and its people.

 

Combating Online Harms in Young Professionals in New Zealand

Our team is working with Netsafe, an online safety charity, to address online harms faced by 18-30-year-olds of Chinese descent in New Zealand. Netsafe works alongside government and law enforcement to address online safety. Due to a lack of continuity of online safety educational programs, young professionals
Ford Dorsey Master's in International Policy students Sebastian Ogando, Raul Ruiz-Solis, Chase Lee, and Aya Purwandaya (not pictured).
Sebastian Ogando, Raul Ruiz-Solis, Chase Lee, and Aya Purwandaya (not pictured)

need resources to be aware of online risks and the best measures to protect themselves. Netsafe has yet to find the most effective way to appeal to this demographic group.

We aim to understand the demographic's most frequently used online platforms, the most common types of online harms, cultural factors, and relevant stakeholders.

 

Understanding Commercial Influence Operations on Social Media from China

Our MIP capstone team is working with DoubleThink Lab in Taiwan to map the ecosystem of People's Republic of China (PRC)-backed commercial influence operations on social media. Currently so-called "dark PR" firms can support PRC
Ford Dorsey Master's in International Policy students Nickson Quak, Gaute Friis, Sara Shah, and Elliot Stewart.
Nickson Quak, Gaute Friis, Sara Shah, and Elliot Stewart

disinformation operations with near impunity. We’re particularly interested in how the development of new tools and tactics – like commercial firms’ use of paid influencers, or generative AI – will aid in further obscuring attribution and scaling operations. Our policy recommendations will address how governments, international organizations, and platforms can tackle this issue.

 

Common Governance Mechanisms for AI in Brazil

Our team is working with the Institute for Technology and Society of Rio de Janeiro (ITS) and the Public Defender's Office (PDO-RJ) in the State of Rio de Janeiro to develop a common governance mechanism for the implementation of artificial intelligence (AI)
Ford Dorsey Master's in International Policy students Poramin Insom, Justin Yates, Thay Graciano, and Rosie Lebel.
Poramin Insom, Justin Yates, Thay Graciano, and Rosie Lebel

tools. Our research focuses on how the different state PDOs in Brazil can collaborate and share AI tools to help reduce their demand and better serve their clients. The goal is for AI to be a "shared public infrastructure" that multiple PDOs can use to serve their clients.

 

Creating Accessible, Affordable Transport Systems in Ghana

Our team is working with the Ghana Center for Democratic Development to understand opportunities for commute time relief in Accra's congested traffic. Our current challenge is identifying sources of improvement in the transit system and
Ford Dorsey Master's in International Policy students Skylar Coleman, Rosie Ith, and Maya Rosales.
Skylar Coleman, Rosie Ith, and Maya Rosales

integrating solutions available at scale for the public. We aim to recommend policy interventions which reflect local demand, ensuring sustainable, efficient, and accessible transportation solutions for the community.

 

Overgrazing and Climate Change in Mongolia

Our capstone focuses on overgrazing in Mongolia where disruptions to the traditional practices of nomadic tribes threaten grassland health. Disruptions include the free market incentivizing increasing herd sizes and climate change reducing the quantity and diversity of vegetation. In the absence of strong
Ford Dorsey Master's in International Policy students Ashwini Thakare, Olivia Hampsher-Monk, Kelsey Freeman, and Sarah Brakebill-Hacke.
Ashwini Thakare, Olivia Hampsher-Monk, Kelsey Freeman, and Sarah Brakebill-Hacke

government interventions, local control of stock numbers, or strong market incentives, herds exceed the grassland carrying capacity in pockets that are becoming increasingly degraded. This threatens nomadic pastoralism, a traditional way of life. With such complex and interlinked drivers to this problem, it has been challenging to isolate the causes we should focus on. We have been working with our partners at The Asia Foundation who are in the early stages of piloting a solution.

 

Solar Mini-grids and Renewable Energy in Sierra Leone

We’re partnering with Sustainable Energy for All, who have identified solar mini-grids as a necessary tool to achieve greater energy access in Sierra Leone. Previous efforts to improve the market for mini-grids have focused on regulatory reform and financial backing from diverse donors. Unfortunately,
Ford Dorsey Master's in International Policy students Felipe Galvis-Delgado, Javier Cantu, Pamella Ahairwe, and Ibilola Owoyele.
Felipe Galvis-Delgado, Javier Cantu, Pamella Ahairwe, and Ibilola Owoyele

these interventions have not led to a widespread growth in mini-grid development, as the industry continues to struggle. We hope to further explore the market and regulatory landscape and learn how sub-interventions including cross-subsidization, de-risking investment, demand creation, and other innovative and locally-based solutions may help improve the industry’s viability and aid in increasing access to affordable, renewable energy in Sierra Leone.

 

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

The Ford Dorsey Master's in International Policy Class of 2025 at the Freeman Spogli Institute for International Studies.
Blogs

Meet the Ford Dorsey Master's in International Policy Class of 2025

From tackling challenges caused by climate change to honing leadership skills for the armed services, the Class of 2025 has arrived at Stanford and is ready to get to work.
Meet the Ford Dorsey Master's in International Policy Class of 2025
Raul Ruiz at Duco Internship
Blogs

Thinking Like a CEO: Navigating San Francisco's Start-Up and Technology Landscape

Interning at Duco Experts, Raúl Ruiz-Solís (Master's in International Policy '24) gained an understanding of the start-up ecosystem in San Francisco, as well as some of the most pressing areas of opportunity in the field of cybersecurity and emerging technologies.
Thinking Like a CEO: Navigating San Francisco's Start-Up and Technology Landscape
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
All News button
1
Subtitle

Taiwan, New Zealand, and Sierra Leone are just a few of the places students from the Ford Dorsey Master's in International Policy are headed this year for their capstone projects.

Regenerative Agriculture: Bringing Indigenous Practice to Food Systems

-

The Human and Planetary Health initiative at the Stanford Woods Institute for the Environment is hosting a dialogue with Chris Field, Director of the Stanford Woods Institute for the Environment and Reginaldo Haslett-Marroquin, an expert in regenerative poultry production and practicing regenerative farmer. Learn more and register on the event page.

Y2E2 Rm 300

Christopher B. Field

Jerry Yang & Akiko Yamazaki Environment & Energy Bldg.
473 Via Ortega, Room 221
Stanford, CA 94305
Phone: 650.736.4352

0
Perry L. McCarty Director of the Stanford Woods Institute for the Environment.; Professor for Interdisciplinary Environmental Studies, School of Earth, Energy & Environmental Sciences; FSI Senior Fellow, by courtesy
chris_field.png
PhD

Chris Field is the Perry L. McCarty Director of the Stanford Woods Institute for the Environment.

His research focuses on climate change, ranging from work on improving climate models, to prospects for renewable energy systems, to community organizations that can minimize the risk of a tragedy of the commons.

Field has been deeply involved with national and international scale efforts to advance science and assessment related to global ecology and climate change. He served as co-chair of Working Group II of the Intergovernmental Panel on Climate Change from 2008-2015, where he led the effort on the IPCC Special Report on “Managing the Risks of Extreme Events and Disasters to Advance Climate Change Adaptation” (2012) and the Working Group II contribution to the IPCC Fifth Assessment Report (2014) on Impacts, Adaptation, and Vulnerability.

Field assumed leadership of the Stanford Woods Institute for the Environment in September 2016. His other appointments at Stanford University include serving as the Melvin and Joan Lane Professor for Interdisciplinary Environmental Studies in the School of Humanities and Sciences; Professor of Earth System Science in the School of Earth, Energy & Environmental Sciences; and Senior Fellow with the Precourt Institute for Energy. Prior to his appointment as Woods' Perry L. McCarty Director, Field served as director of the Carnegie Institution for Science's Department of Global Ecology, which he founded in 2002. Field's tenure at the Carnegie Institution dates back to 1984.

His widely cited work has earned many recognitions, including election to the U.S. National Academy of Sciences, the Max Planck Research Award, the American Geophysical Union’s Roger Revelle Medal and the Stephen H. Schneider Award for Outstanding Science Communication. He is a fellow of the American Academy of Arts and Sciences, the American Association for the Advancement of Science, and the Ecological Society of America.

Field holds a bachelor’s degree in biology from Harvard College and earned his Ph.D. in biology from Stanford in 1981.

Panel Discussions

Lasering In on Corn Fields

News Type
News
Date
Hero Image
All News button
1
Subtitle

Mapping crops around the globe is key to estimating production and developing targeted management strategies. New research utilized data from NASA's Global Ecosystem Dynamics Investigation (GEDI) technology and developed an algorithm to distinguish between maize and other crops with high accuracy and produce crop maps across the globe.

A 20-year retrospective review of global aquaculture

All Publications button
1
Publication Type
Journal Articles
Publication Date
Subtitle

The sustainability of aquaculture has been debated intensely since 2000, when a review on the net contribution of aquaculture to world fish supplies was published in Nature. This paper reviews the developments in global aquaculture from 1997 to 2017, incorporating all industry sub-sectors and highlighting the integration of aquaculture in the global food system. Inland aquaculture—especially in Asia—has contributed the most to global production volumes and food security. Major gains have also occurred in aquaculture feed efficiency and fish nutrition, lowering the fish-in–fish-out ratio for all fed species, although the dependence on marine ingredients persists and reliance on terrestrial ingredients has increased. The culture of both molluscs and seaweed is increasingly recognized for its ecosystem services; however, the quantification, valuation, and market development of these services remain rare. The potential for molluscs and seaweed to support global nutritional security is underexploited. Management of pathogens, parasites, and pests remains a sustainability challenge industry-wide, and the effects of climate change on aquaculture remain uncertain and difficult to validate. Pressure on the aquaculture industry to embrace comprehensive sustainability measures during this 20-year period have improved the governance, technology, siting, and management in many cases.

Journal Publisher
Nature
Authors
Rosamond L. Naylor

Combining GEDI and Sentinel-2 for wall-to-wall mapping of tall and short crops

All Publications button
1
Publication Type
Journal Articles
Publication Date
Subtitle
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 sensors, often exhibit low performance when transferred. Here we explore the use of NASA's Global Ecosystem Dynamics Investigation (GEDI) spaceborne lidar instrument, combined with Sentinel-2 optical data, for crop type mapping. Using data from three major cropped regions (in China, France, and the United States) we first demonstrate that GEDI energy profiles are capable of reliably distinguishing maize, a crop typically above 2m in height, from crops like rice and soybean that are shorter. We further show that these GEDI profiles provide much more invariant features across geographies compared to spectral and phenological features detected by passive optical sensors. GEDI is able to distinguish maize from other crops within each region with accuracies higher than 84\%, and able to transfer across regions with accuracies higher than 82\% compared to 64\% for transfer of optical features. Finally, we show that GEDI profiles can be used to generate training labels for models based on optical imagery from Sentinel-2, thereby enabling the creation of 10m wall-to-wall maps of tall versus short crops in label-scarce regions. As maize is the second most widely grown crop in the world and often the only tall crop grown within a landscape, we conclude that GEDI offers great promise for improving global crop type maps.
Journal Publisher
Environmental Research Letters
Authors
Stefania Di Tommaso
David Lobell
Sherrie Wang

Global warming increased U.S. crop insurance losses by $27 billion in 27 years, Stanford study finds

Authors
Josie Garthwaite
News Type
News
Date
Hero Image
All News button
1
Subtitle

Higher temperatures attributed to climate change caused payouts from the nation’s biggest farm support program to increase by $27 billion between 1991 and 2017, according to new estimates from Stanford researchers. Costs are likely to rise even further with the growing intensity and frequency of heat waves and other severe weather events.

Two shifts for crop mapping: Leveraging aggregate crop statistics to improve satellite-based maps in new regions

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

A million kernels of truth: Insights into scalable satellite maize yield mapping and yield gap analysis from an extensive ground dataset in the US Corn Belt

All Publications button
1
Publication Type
Journal Articles
Publication Date
Subtitle
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 yield monitors collect real-time yield data during harvest with high spatial resolution, generating a large ground dataset. Here, we leveraged a yield monitor dataset of over one million maize field observations across the United States Corn Belt from 2008 to 2018 to evaluate the Scalable Crop Yield Mapper (SCYM). SCYM uses region-specific crop model simulations and climate data to interpret vegetation indices from satellite observations, thus enabling efficient sub-field yield estimation across large regions and multiple years without reliance on ground data calibration. We used the ground dataset to compare alternative SCYM model implementations, define minimum required satellite observation criteria, and evaluate the sensitivity of satellite-based yield estimates to on-the-ground variation in management, soil, and annual weather. We found that smoothing annual time series data with harmonic regression increased 30 m pixel-level accuracy from r2 = 0.31 to 0.40 and reduced dependency on specific satellite observation timing, enabling robust yield estimation on 97% of annual maize area using only Landsat data. Agreement improved as the assessment was aggregated to field-level (r2 = 0.45) and county-level (r2 = 0.69) scales, demonstrating the need for fine-resolution ground truth data to better assess sub-field level accuracy in high resolution products. We found that SCYM and ground data showed a similar yield response to management and environmental variation, particularly capturing linear and nonlinear responses to sowing density, soil water holding capacity, and growing season precipitation. However, sensitivity to factors like soil quality and planting date was muted for SCYM estimates compared to ground-based yields. Random forest models were able to match SCYM performance when trained on at least 1000 ground observations, but performed poorly when tested on years and locations not represented in the training data. Our results demonstrate that satellite yield maps can provide much-needed information on multidecadal yield trends and inform yield gap analyses.
Journal Publisher
Remote Sensing of Environment
Authors
David Lobell
Subscribe to Agriculture