Increasing numbers and intensity of forest fires indicate that forests have become susceptible to fires in the tropics. We assessed the susceptibility of forests to fire in India by comparing six machine learning (ML) algorithms. We identified the best-suited ML algorithms for triggering a fire prediction model, using minimal parameters related to forests, climate and topography. Specifically, we used Moderate Resolution Imaging Spectroradiometer (MODIS) fire hotspots from 2001 to 2020 as training data. The Area Under the Receiver Operating Characteristics Curve (ROC/AUC) for the prediction rate showed that the Support Vector Machine (SVM) (ROC/AUC = 0.908) and Artificial Neural Network (ANN) (ROC/AUC = 0.903) show excellent performance. By and large, our results showed that north-east and central India and the lower Himalayan regions were highly susceptible to forest fires. Importantly, the significance of this study lies in the fact that it is possibly among the first to predict forest fire susceptibility in the Indian context, using an integrated approach comprising ML, Google Earth Engine (GEE) and Climate Engine (CE).
Key message Teak (Tectona grandis L. f.) is a native tree species of India. It is one of the most desirable timber species because of its strength, fine texture, and durability. Its growth is strongly dependent on the climatic conditions, but empirical data are often unavailable to support management decisions. The physiological principles for predicting growth incorporated in the 3-PGmix model make it a useful tool in modelling the growth responses and management in the changing climate. We assessed that under elevated atmospheric carbon dioxide (CO 2 ) concentration and no thinning, teak would store more carbon than currently. Context Uncertainty and lack of scientific understanding about the growth response to climate change and thinning regimes have created challenges in teak sustainability, both regionally and globally. Aims This research examines climate change and management implications on teak growth in India using the 3-PGmix model. Methods The 3-PGmix model was coupled with climate scenarios (Representative Concentration Pathway (RCP) 4.5 and 8.5) to forecast growth response up to the year 2100 with 1981-2010 as the baseline under thinning (G-quality, P-quality) regimes. Thinning under G-quality is performed at earlier stand age than P-quality, and then simulations under 'no thinning' based on stocking/ha at different thinning intensity. Results Under 'no thinning', predicted net primary productivity (NPP) for RCP4.5 and RCP8.5 became 5.77 t/ha/year and 5.28 t/ha/year in 2100. However, under increasing CO 2 , it became 7.39 t/ha/year and 8.22 t/ha/year respectively in 2100. In the future, increasing CO2 would be the dominating factor for an increase in teak growth; however, abnormal precipitation and warmer temperature could produce an unforeseen growth condition. The carbon stock and CO 2 sequestration are predicted to be higher under no thinning, which signifies the CO 2 fertilisation effect in teak.
ConclusionThe set of parameters used in 3-PGmix offers an opportunity to predict teak responses to future climatic conditions and management treatments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.