Research Overview

We seek to understand how land systems are changing, what drives those changes, and what they mean for sustainability and equity. Our work integrates multi-sensor remote sensing (optical, SAR, lidar, drone), geospatial artificial intelligence, field reference, and land system science to generate decision-relevant maps and insights.​

Geospatial artificial intelligence

Geospatial AI is a key part of the SensLand Lab’s work. With support from agencies including NASA and NSF, we focus on:
​
Foundation models for environmental monitoring
We evaluate and advance Earth observation foundation models (e.g., TerraMind) for automated, generalizable change monitoring. We test how multimodal time series and learned representations improve robustness.

Fine-scale mapping through drone–satellite fusion
We fuse drone imagery and satellite time series with geospatial AI to map small or fragmented targets (e.g., invasive trees, localized burn scars), supporting ecology, conservation, and hazard-risk reduction where fine detail matters.

Bridging satellites and field reference
We build label-efficient workflows that link ground evidence (e.g., GoPro videos, surveys, targeted site visits) with satellite data to reduce annotation burden and strengthen credibility.

Land use dynamics

​We map and explain land use dynamics on working landscapes, with an emphasis on agricultural transitions and management that are difficult to observe. 

Cropland abandonment
Cropland abandonment is a widespread land-use change with major impacts on carbon storage, biodiversity, and rural livelihoods. We use satellite time series to map abandonment precisely in time and space—and use these maps to support broader environmental and socioeconomic applications.

Related publications:

• Crawford, C. Wiebe, A. Yin, H. Radeloff, V. Wilcove, D. (2024): Biodiversity consequences of cropland abandonment. Nature Sustainability . 7: 596–1607
• Yin, H. de Oliveira Brandao Jr., A. Buchner, B. Helmers, D. Luliano, B. G. Kimambo, N. Lewińska, K. E. Razenkova, E. Rizayeva, A. Rogova, N. Spawn, S. A. Xie, Y. H. and Radeloff, V. C. (2020): Monitoring cropland abandonment with Landsat time series. Remote Sensing of Environment. 246: 111873
• Yin, H. Prishchepov, A. Kuemmerle, T. Bleyhl, B. Buchner, J. and Radeloff, V. (2018): Mapping agricultural land abandonment from spatial and temporal segmentation of Landsat time series. Remote Sensing of Environment. 210: 12-24​

Grassland management
Grasslands provide major ecosystem services, and a key management question is where and when mowing occurs. We develop methods to detect mowing events using dense satellite time series, leveraging the complementary coverage of Landsat and Sentinel-2.
​Related publications: 

• Yin, H. Griffiths, P. Hoster, P and Radeloff, V. C. (in preparation): Mapping grassland use with Landsat and Sentinel-2 time series.

---

The Sentinel-2 imagery showing grassland dynamics in France

The enhanced vegetation index time series showing mowing events

Disaster monitoring​​

Abandoned and damaged cropland surrounding a war-torn village in Syria

Societal disaster such as armed conflicts can reshape land systems through destruction, displacement, and market disruption, with direct implications for food security and recovery. We combine remote sensing, causal/impact-oriented inference, and field evidence (when feasible) to quantify where, when, and how conflict affects agricultural land and civilian livelihoods.
​
Related publications:

• ​​​Yin, H. Eklund, L, Habash, D. Qumsiyeh, M. Van Den Hoek, J. (2025): Evaluating war-induced damage to agricultural land in the Gaza Strip since October 2023 using PlanetScope and SkySat imagery. Science of Remote Sensing. 11: 100199
• Buchner, J. Butsic,  Yin, H. V. Kuemmerle, A. Baumann, Zazanashvili, N. Stapp, J. and Radeloff, V. (2022): Localized versus wide-ranging effects of the post-Soviet wars in the Caucasus on agricultural abandonment. Global Environmental Change. 76: 102580
• Yin, H. Butsic, V. Buchner, J. Kuemmerle, T. Prishchepov, A. Baumann, M. Bragina, E. Sayadyan, H. and Radeloff, V. (2019): Agricultural abandonment and re-cultivation during and after the Chechen Wars in the northern Caucasus. Global Environmental Change. 55: 149-159

---

Funding

2025-2027 Yin, H. (PI). Collaborative Research: NSF R2I2: Managing Invasive Caribbean Pine to Reduce Wildfire Risk in Puerto Rico. National Science Foundation (NSF)

2025-2027 Yin, H. (Co-I). Scalable conflict damage monitoring with open EO data. NASA Science Mission Directorate Single-Source. National Aeronautics and Space Administration (NASA)
​
2021-2026 Yin, H. (PI). The effects of the Syrian civil war on cropland in the eastern Mediterranean region. NASA New (Early Career) Investigator Program in Earth Science

2020-2021 Yin, H. (PI). Mapping cropland abandonment in Eurasia. Lawrence Livermore National Laboratory

2018-2023 Radeloff, V (PI). Monitoring the dynamics of abandoned agriculture, fallow fields and grasslands, with harmonized Landsat and Sentinel-2 data. NASA Land-Cover and Land-Use Change Program (LCLUC) Multi-Source Land Imaging Science

2018-2022 Radeloff, V. (PI). Long-term land degradation in the Caucasus. NASA Land-Cover and Land-Use Change Program (LCLUC)

2016-2017 Zuckerberg, B. (PI). Re-wilding urban environments: Integrating remote sensing and citizen science to study the environmental context and ecological consequences of returning avian predators. NASA Citizen Science for Earth Systems Program

We are grateful for the support from