X Han, Y Guo, C Mi, F Huettmann, L Wen - Scientific reports, 2017 - nature.com
… Using machinelearning methods and the best-available data from our 7,000-kilometer mega-transect survey and open access data, we built the first species distribution model (SDM) to …
Y Uwiragiye, MJY Ngaba, M Zhao, AS Elrys… - Catena, 2022 - Elsevier
… machinelearning to predict soil nutrient depletion for Rwanda. The “caretEnsemble” package is a machinelearning … The Congo watershed division, Birunga and Central plateau AEZs …
… ground truth and RS data in a non-parametric machinelearning algorithm approach. Random forest, a non-parametric machinelearning algorithms were used to predict Teff yield at the …
… This study explored the use of remote sensing imagery and machinelearning (ML) … Six machinelearning (ML) algorithms integrated with Landsat 8 imagery were evaluated for …
W Huang, W Li, J Xu, X Ma, C Li, C Liu - Remote Sensing, 2022 - mdpi.com
… models are similar, with the GPR machinelearning model achieving the best outcomes. In … Finally, by constructing a machinelearning interpretable model to analyze the specific role …
ML Mann, JM Warner, AS Malik - Climatic change, 2019 - Springer
… We train machinelearning models to predict the likelihood of losses and explore the most influential variables. On independent samples, the models identify substantial drought loss …
… feature selection approach along with tree machinelearning approaches including random forest (… Secondly, compared with the performances of the robust tree-based machinelearning …
… to predict soil erosion susceptibility in the CentralHighlands of Sri Lanka under different … equation, statistical, machinelearning and hybrid machinelearning techniques to predict soil …
… This study investigates the applicability of various geospatial data, machinelearning techniques (MLTs) and spatial statistical tools to demarcate the forest fire susceptible regions of the …