Remote sensing-based biomass estimation of dry deciduous tropical forest using machine learning and ensemble analysis
Forests play a vital role in maintaining the global carbon balance. However, globally, forest ecosystems are increasingly threatened by climate change and deforestation in recent years. Monitoring forests, specifically forest biomass is essential for tracking changes in carbon stocks and the global carbon cycle. However, developing countries lack the capacity to actively monitor forest carbon stocks, which ultimately adds uncertainties in estimating country specific contribution to the global carbon emissions. In India, authorities use field-based measurements to estimate biomass, which becomes unfeasible to implement at finer scales due to higher costs.
To address this, the present study proposed a framework to monitor above-ground biomass (AGB) at finer scales using open-source satellite data. The framework integrated four machine learning (ML) techniques with field surveys and satellite data to provide continuous spatial estimates of AGB at finer resolution. The application of this framework is exemplified as a case study for a dry deciduous tropical forest in India. The results revealed that for wet season Sentinel-2 satellite data, the Random Forest (adjusted R2 = 0.91) and Artificial Neural Network (adjusted R2 = 0.77) ML models were better-suited for estimating AGB in the study area. For dry season satellite data, all the ML models failed to estimate AGB adequately (adjusted R2 between −0.05 – 0.43). Ensemble analysis of ML predictions not only made the results more reliable, but also quantified spatial uncertainty in the predictions as a metric to identify its robustness.
Research news | 2023-10-03
Combining modeling and empirical research can give better sustainability insights
Mixing empirical methods and modeling can provide better insights into cause-effect relationships in sustainability, and improve governance
General news | 2023-09-19
New Google.org grant funds Centre research on AI-powered climate risk tool
Google.org has awarded five million US dollars to a group of scientists, including Centre researchers, to develop and scale ClimateIQ , an artificial intelligence-powered climate risk evaluation tool for cities
General news | 2023-09-19
Researchers and chefs team up for a sustainable lunch week
“Risotto on Swedish oat-rice, with apple cider vinegar, blue mussels from Bohuslän, parsley, and grated Svecia cheese”. That’s one of the science-cooked dishes that guests can enjoy at “A Planetary Lunch” — an experimental lunch week at Stockholm university
Research news | 2023-09-14
The SDGs are not on track — new report outlines what needs to happen
Humanity is set to miss the Sustainable Development Goals. But decisive and timely policy actions can kickstart extraordinary turnarounds and a giant leap toward achieving the SDGs
Research news | 2023-09-13
All planetary boundaries mapped out for the first time, six of nine crossed
For the first time, an international team of scientists is able to provide a detailed outline of planetary resilience by mapping out all nine boundary processes that define a safe operating space for humanity.
General news | 2023-09-04
Centre secures 28 MSEK research funding in two new Formas grants
The two grants worth 14 million SEK each will focus on the intersection of climate, water and biodiversity