A5025961099- Data-Driven Disease Surveillance
- Human Mobility and Location-Based Analysis
- COVID-19 epidemiological studies
- Remote Sensing in Agriculture
- Smart Agriculture and AI
- Remote Sensing and Land Use
- Mobile and Web Applications
- Food Supply Chain Traceability
- Agricultural Systems and Practices
- Distributed and Parallel Computing Systems
- Atmospheric chemistry and aerosols
- Air Quality Monitoring and Forecasting
- Atmospheric and Environmental Gas Dynamics
- Land Use and Ecosystem Services
Google (United States)
2020-2024
Disease dynamics, human mobility, and public policies co-evolve during a pandemic such as COVID-19. Understanding dynamic mobility changes spatial interaction patterns are crucial for understanding forecasting COVID-19 dynamics. We introduce novel graph-based neural network(GNN) to incorporate global aggregated flows better of the impact on dynamics well disease propose recurrent message passing graph network that embeds spatio-temporal daily state-level new confirmed cases forecasting. This...
This work quantifies mobility changes observed during the different phases of pandemic world-wide at multiple resolutions -- county, state, country using an anonymized aggregate map that captures population flows between geographic cells size 5 km 2 . As we overlay global with epidemic incidence curves and dates government interventions, observe as case counts rose, fell has since then seen a slow but steady increase in flows. Further, order to understand mixing within region, propose new...
The Mumbai Suburban Railways, \emph{locals}, are a key transit infrastructure of the city and is crucial for resuming normal economic activity. To reduce disease transmission, policymakers can enforce reduced crowding mandate wearing masks. \emph{Cohorting} -- forming groups travelers that always travel together, an additional policy to transmission on \textit{locals} without severe restrictions. Cohorting allows us to: ($i$) form traveler bubbles, thereby decreasing number distinct...
Accurate and timely information about expected crop production is crucial for various applications including agricultural monitoring, policy making, food security assessment. Policy makers can use near-real time maps to better determine support prices, storage infrastructure, imports. In the context of India, absence farm-level r government work with aggregate statistics based on manual surveys, therefore are fundamentally limited in scale accuracy. Surveys over large regions such as entire...
Land-use understanding at agricultural field level is critical for decision making and addressing food water security challenges, especially in smallholder regions. Using remote sensing modern machine learning practices the same an active area of research. Satellite crop classification models are built using ground truth from manual surveys namely location, timestamp label. However prone to labeling errors unlikely be scalable due cost prohibitions. Since don’t generalize a sparse...
Agricultural landscapes are quite complex, especially in the Global South where fields smaller, and agricultural practices more varied. In this paper we report on our progress digitizing landscape (natural man-made) study region of India. We use high resolution imagery a UNet style segmentation model to generate first its kind national-scale multi-class panoptic output. Through work have been able identify individual across 151.7M hectares, delineating key features such as water resources...
In the domain of precision agriculture, land-use planning, and resource management, precise delineation field boundaries is pivotal for informed decision-making. The dynamic nature agricultural landscapes, particularly in smallholder farming, introduces seasonal changes that pose challenges to accurately identify update boundaries. conventional approach relying on high-resolution imagery this purpose proves be economically impractical a basis. We propose framework utilizes spatiotemporal...