Machine learning for digital soil map**: Applications, challenges and suggested solutions

AMJC Wadoux, B Minasny, AB McBratney - Earth-Science Reviews, 2020 - Elsevier
The uptake of machine learning (ML) algorithms in digital soil map** (DSM) is
transforming the way soil scientists produce their maps. Within the past two decades, soil …

[HTML][HTML] Benthic habitat map**: A review of three decades of map** biological patterns on the seafloor

B Misiuk, CJ Brown - Estuarine, Coastal and Shelf Science, 2024 - Elsevier
What is benthic habitat map**, how is it accomplished, and how has that changed over
time? We query the published literature to answer these questions and synthesize the …

Global prevalence of non-perennial rivers and streams

ML Messager, B Lehner, C Cockburn, N Lamouroux… - Nature, 2021 - nature.com
Flowing waters have a unique role in supporting global biodiversity, biogeochemical cycles
and human societies,,,–. Although the importance of permanent watercourses is well …

[HTML][HTML] Spatial flood susceptibility map** using an explainable artificial intelligence (XAI) model

B Pradhan, S Lee, A Dikshit, H Kim - Geoscience Frontiers, 2023 - Elsevier
Floods are natural hazards that lead to devastating financial losses and large displacements
of people. Flood susceptibility maps can improve mitigation measures according to the …

Spatial validation reveals poor predictive performance of large-scale ecological map** models

P Ploton, F Mortier, M Réjou-Méchain, N Barbier… - Nature …, 2020 - nature.com
Map** aboveground forest biomass is central for assessing the global carbon balance.
However, current large-scale maps show strong disparities, despite good validation statistics …

Predicting into unknown space? Estimating the area of applicability of spatial prediction models

H Meyer, E Pebesma - Methods in Ecology and Evolution, 2021 - Wiley Online Library
Abstract Machine learning algorithms have become very popular for spatial map** of the
environment due to their ability to fit nonlinear and complex relationships. However, this …

Spatial cross-validation is not the right way to evaluate map accuracy

AMJC Wadoux, GBM Heuvelink, S De Bruin… - Ecological Modelling, 2021 - Elsevier
For decades scientists have produced maps of biological, ecological and environmental
variables. These studies commonly evaluate the map accuracy through cross-validation with …

[HTML][HTML] Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks

J Mäyrä, S Keski-Saari, S Kivinen… - Remote Sensing of …, 2021 - Elsevier
During the last two decades, forest monitoring and inventory systems have moved from field
surveys to remote sensing-based methods. These methods tend to focus on economically …

[HTML][HTML] Urban flood modeling using deep-learning approaches in Seoul, South Korea

X Lei, W Chen, M Panahi, F Falah, O Rahmati… - Journal of …, 2021 - Elsevier
Identification of flood-prone sites in urban environments is necessary, but there is insufficient
hydraulic information and time series data on surface runoff. To date, several attempts have …

[HTML][HTML] Using explainable machine learning to understand how urban form shapes sustainable mobility

F Wagner, N Milojevic-Dupont, L Franken… - … Research Part D …, 2022 - Elsevier
Municipalities are increasingly acknowledging the importance of urban form interventions
that can reduce intra-city car travel in achieving more sustainable cities. Current academic …