Select Research
Decision-Oriented Benchmarking to Transform AI Weather Forecast Access: Application to the Indian Monsoon
February 2026
Open-access artificial intelligence weather prediction (AIWP) models hold promise as transformational tools for helping low- and middle-income populations make decisions in the face of high-impact weather shocks. Yet, current approaches to evaluating AIWP models focus mainly on aggregated meteorological metrics without considering local stakeholders’ needs in decision-oriented, operational frameworks. Here, we introduce such a framework that connects meteorology, AI, and social sciences.
Designing Probabilistic AI Monsoon Forecasts to Inform Agricultural Decision-Making
January 2026
Hundreds of millions of farmers make high-stakes decisions under uncertainty about future weather. Forecasts can inform these decisions, but available choices and their risks and benefits vary between farmers. We introduce a decision-theory framework for designing useful forecasts in settings where the forecaster cannot prescribe optimal actions because farmers’ circumstances are heterogeneous.
Addressing Heterogeneity in Learning Levels through Personalized Adaptive Learning
September 2025
Personalized Adaptive Learning (PAL) software is a tech tool that adapts educational content to each student’s learning level. It continuously diagnoses performance and learning levels of the student and adjusts instructional content and practice questions to address gaps or provide advanced content. In doing so, PAL helps bridge learning deficits in classrooms with wide variation in student ability. The Government of Andhra Pradesh (GoAP) adopted Personalized Adaptive Learning in 2019 for students in Grades 6–9 in mathematics, English, and Telugu.
In 2023, the Development Innovation Lab partnered with Samagra Shiksha, GoAP’s Department of School Education, and Central Square Foundation to evaluate PAL’s impact on math learning.