The ISPRS SC Webinar Series
ISPRS WG III/4 Webinar on Land Use and Land Cover Change Detection
This webinar is organised by ISPRS TC III/WG 4 and supported by ISPRS Student Consortium (ISPRS SC). The webinar consists of two presentations as follows:
Title 1: Cropland expansion in Ecuador between 2000 and 2016
Abstract: We describe changes in the cropland distribution for physiographic and bioregions of continental Ecuador between 2000 and 2016 using Landsat satellite data and government statistics. The cloudy conditions in Ecuador are a major constraint to satellite data analysis. We developed a two-stage cloud filtering algorithm to create cloud-free multi-temporal Landsat composites that were used in a Random Forest model to identify cropland. The overall accuracy of the model was 78% for the Coast region, 86% for the Andes, and 98% for the Amazon region. Cropland density was highest in the coastal lowlands and in the Andes between 2500 and 4400 m. During this period, cropland expansion was most pronounced in the Páramo, Chocó Tropical Rainforests, and Western Montane bioregions. There was no cropland expansion detected in the Eastern Foothill forests bioregion. The satellite data analysis further showed a small contraction of cropland (4%) in the Coast physiographic region, and cropland expansion in the Andes region (15%), especially above 3500m, and in the Amazon region (57%) between 2000 and 2016. The government data showed a similar contraction for the Coast (7%) but, in contrast with the satellite data, they showed a large agricultural contraction in the Andes (39%) and Amazon (50%). While the satellite data may be better at estimating relative change (trends), the government data may provide more accurate absolute numbers in some regions, especially the Amazon because separating pasture and tree crops from forest with satellite data is challenging. These discrepancies illustrate the need for careful evaluation and comparison of data from different sources when analyzing land use change.
Speaker’s Bio : José Ochoa-Brito, PhD is an Ecuadorian physical geographer who works in the fields of environmental remote sensing, spatial data science and vegetation spectroscopy. He has wide experience in diverse research projects using optical and radar satellite data with machine learning methods. His most recent work includes carbon emission units calculation and Verra methodologies implementation for Revalue, UK, land cover change analysis in the Ecuadorian amazon for University of California, Merced, and forest dynamics and land use modeling in the Amazon region as a SESYNC research fellow. He has also worked in evaluating and developing evapotranspiration (ET) models in humid subtropical and semi-arid climates within the DEVELOP program from NASA, and for the Department of Land, Air, and Water Resources, University of California, Davis (UC Davis) as a graduate student researcher. José holds a PhD in Geography from UC Davis, a Master in Remote Sensing from Universitat de Valencia, and BEng. in Computer Sciences from Universidad de Cuenca.
Topic 2: Shifts in water supply and demand shape land cover change across Chile
Abstract: Droughts worldwide are lasting longer, occurring more often, and becoming more intense, with far-reaching effects. Beyond water availability, prolonged and cumulative changes in the water balance can trigger significant shifts in land cover. We assessed how temporal changes in water supply and demand at multiple time scales affect vegetation productivity and land cover changes in continental Chile, which has faced severe drought since 2010. Since 2000, most of the region has experienced a persistent decline in water supply and an increase in atmospheric water demand. However, in water-limited ecoregions, vegetation water demand has decreased over time, with this trend intensifying over longer time scales. This long-term reduction in water availability and shifting water demand have led to declining vegetation productivity, especially in the Chilean Matorral and the Valdivian temperate forest ecoregions. We found that drought indices related to soil moisture and actual evapotranspiration at time scales of up to 12 months primarily explain these declines. Further, our results indicate that drought intensity accounts for up to 78% of shrubland and 40% of forest area changes across all ecoregions. The most important variable explaining cropland changes is the burned area. Our results suggest that long-term climate change will impact even drought-tolerant vegetation, underscoring the need for context-specific adaptation strategies in agriculture, biodiversity conservation, and natural resource management.
Speaker’s Bio: He serves as an associate professor and researcher at the Hemera Center for Earth Observation, and teaches both the master's program in remote sensing and the PhD program in integrative ecology at Universidad Mayor. He holds a PhD in agricultural engineering with a specialization in water resources, both from the University of Concepción, Chile. He conducts research on the impact of climate on agricultural and natural vegetation throughout Chile using Earth observation data sources.
