Search

Accurate assessment of aboveground biomass (AGB) in tropical forests, particularly within a biodiversity hotspot, is vital for sustainable resource management and the preservation of ecosystems. However, estimating AGB in tropical forests is complex due to the diverse and intricate nature of vegetation, necessitating the integration of data from multiple sources. To tackle this challenge, our study utilized seven machine learning algorithms to analyze various combination of multisource datasets. We developed seven models/scenarios that incorporated Sentinel-1, Sentinel-2 as well as environmental factors such as topography, soil and climate to identify key variables for accurate estimation of AGB. For optimal performance, hyperparameters of the algorithms were fine-tuned through 10-fold cross-validation and their accuracy were assessed using the testing dataset. We found that the integrated model of satellite datasets, topography, climate, and soil variables exhibited the highest accuracy, where ensemble stacking, that combined multiple MLAs, proved to be reliable and best suited for predicting AGB (mean absolute error-3.97 Mg 0.1 ha−1, root mean square error-5.67 Mg 0.1 ha−1, and coefficient of determination - 0.82). Notably, the top predictor variables included Sentinel-2 bands (near infrared and green), soil properties (pH and soil organic carbon), and topography (elevation). The study emphasizes the significance of incorporating environmental variables (specifically topography and soil properties) along with Sentinel datasets to improve the accuracy of AGB estimation. This approach has the potential for broader applications, specifically in regions where vegetation productivity is governed by diverse environmental conditions. • An ensemble stacking approach is proposed for AGB estimation for tropical forest • Ensemble model outperformed other MLAs viz., RF,KNN,ANN,GB,MARS,PR,SVM • Combining S2 and S1 with environmental co-variates is the most robust approach for accurately estimating AGB • Topography (elevation) and soil properties (pH and SOC) were among the top predictor variables • AGB estimation accuracy relies on diverse earth observation variables, proper feature selection, and suitable MLAs [ABSTRACT FROM AUTHOR]

• An ensemble model is proposed for forest fire susceptibility modelling in the Western Ghats. • Ensemble model outperformed MAXENT, GLM, RF, MARS, GBM, and ANN. • Land use and land cover was the most important factor in explaining fire severity. • High number of fire occurrences are reported in deciduous forests, which occupy 40% of the landscape. • Machine learning models have been demonstrated as highly recommended tools for forest fire susceptibility modeling. In ecologically sensitive areas like the Western Ghats, fire is largely considered to be the most significant management concern. Therefore, identifying and predicting the fire susceptible areas is crucial for managing protected area networks. In this study, we investigated the factors affecting forest fires and modelled the fire susceptibility in a human-dominated landscape in the central Western Ghats, India, by employing remote sensing, geographic information systems and machine learning techniques. We used six machine learning models (MLMs), including artificial neural network, random forest, generalized linear model, maximum entropy, multivariate adaptive regression splines, gradient boosting machine and the ensemble model, to relate the occurrence data of fires to 14 predictor variables categorized as climate, topography, vegetation, and anthropogenic disturbances to generate fire susceptibility maps. The area under the receiver operating characteristic (AUC-ROC), true skill statistic (TSS) curves, accuracy and continuous Boyce index (CBI) were used to assess the model's accuracy. We found that all models achieved acceptable performance while validating the independent test data. However, ensemble model had the best overall performance with an AUC-ROC = 0.93; TSS = 0.72; ACCURACY = 0.89; and CBI = 0.95. The land-use and land-cover, and the distance to the agricultural fields and settlements were the key determinants of fire occurrences in the study area based on the ensemble model. The results showed that the landscape has a high to very high fire risk for about 26.5% of the total area. Forest fires have mostly occurred in the northeastern regions of the landscape, which are dominated by deciduous forests and plantations, whereas western regions are less susceptible to fires. Finally, we developed an ensemble-based fire susceptibility map with a resolution of 10 m that may be used as a tool for the prevention of forest fires. Further, it aids the relevant authorities in mitigating the disastrous effects and safeguarding the environment. The results demonstrated that ensemble-based MLMs can be employed effectively for fire prediction in other regions. [ABSTRACT FROM AUTHOR]

Tropical forest ecosystems are among the most essential habitats on Earth for conserving biological diversity and short-term climate regulation. For this reason, they are key areas of conservation policies in the world. In this paper, we aim to investigate the dynamics of forest cover and their changes in primary productivity by empowering information on historical forest management and fieldwork research with remote sensing vegetation monitoring methods. The study area falls within the central portion of the Indian Western Ghats, a global biodiversity hotspot. In particular, part of the analysis was performed on the Kadamakal Reserve Forest and Pushpagiri Wildlife Sanctuary, which harbours an endemic low elevation dipterocarp evergreen forest. This area was managed by selective logging and became fully protected in 1984. We performed multiple time series macroscale analyses between 1999 and 2020 on the Indian Central Western Ghats region, using satellite products at 1 km spatial resolution from the VITO Copernicus Global Land Service on Dry Matter Productivity, Fraction of Absorbed Photosynthetically Active Radiation, and Normalised Difference Vegetation Index. We also performed a very-high spatial resolution Normalised Difference Vegetation Index differential analysis between 2021 and 2016 with Sentinel 2-L2A products to investigate forest dynamics within the reserve. At the 1 km spatial resolution has been found an increase in all three vegetation indices, by employing the LOESS statistical method for the smoothed transition autoregressive model of raster data medians of our datasets. The boxplot raster distribution analysis also highlighted a significant imbalance in dry matter productivity in the last decade (2010−2020) comparing the previous one (1999–2009). The second part of the analysis, at 10 m spatial resolution within the reserve forest, revealed a growth in the vegetation cover on the top of the Pushpagiri Mountain ridge and in a previously landslide area. The study found new erosion channels down to the upper plateau on the South-West side of the reserve due to an increment of the run-off processes during the monsoon period. This satellite analysis highlighted generalised positive vegetation trends in the Central Western Ghats, India, over the last twenty-two years, enhancing an improvement in the ecosystem functioning and carbon storage ecosystem service. Notably, through this work, we also developed a standardised and open-access framework to monitor the vegetation remotely (SVIT) during periods of forest inaccessibility for fieldwork sampling. [Display omitted] • Tropical forest ecosystems are hotspots for conserving biological diversity • Natural conservation policies focus on the tropical region's legacy • Remote sensing tools as proxies for monitoring the vegetation functioning • Open-source ecology as a tool for standard methods and information consistency • Highlights of conservation effectiveness efforts in Central Western Ghats, India [ABSTRACT FROM AUTHOR]