Reprint

Integrating GIS and Remote Sensing in Soil Mapping and Modeling

Edited by
December 2022
320 pages
  • ISBN978-3-0365-5978-0 (Hardback)
  • ISBN978-3-0365-5977-3 (PDF)

This book is a reprint of the Special Issue Integrating GIS and Remote Sensing in Soil Mapping and Modeling that was published in

Computer Science & Mathematics
Environmental & Earth Sciences
Summary

The aim of this book is to publish original contributions or review articles that evaluate the integration of GIS and remote sensing in agricultural practice by improving soil quality and environmental health. The complexity of spatial data and modeling methods in soil science imposes the need for combined integrated approaches using robust methods, leading to more accurate and reliable outcomes in sustainable soil management. More specifically, we are interested in studies that investigate the impact of widely applied geographical approaches in everyday soil research and activities. This book addresses many aspects, including soil mapping and the spatial modeling of soil characteristics, precision agriculture, geostatistics, machine learning, and the development of software tools for data collection and processing. Work that directly addresses the response of anthropogenic interventions to ecosystems and climate change is particularly welcome. Theoretical approaches andlab and/or field experimentation cases are equally welcome to this Special Issue, "Integrating GIS and Remote Sensing in Soil Mapping and Modeling".

Format
  • Hardback
License
© 2022 by the authors; CC BY-NC-ND license
Keywords
soil pollution; mining; multispectral images; UAV; vegetation index; soil erosion; erosion pin; ensemble machine learning; Shihmen Reservoir watershed; bagging; boosting; stacking; RUSLE; soil loss; siltation; Zagros; sub-basin; hypsometric integral; agrochemical properties; digital soil mapping; SVM; MLR; topographic variables; SMOS; soil moisture deficit; rainfall-runoff model; random forest; Genetic Algorithm; climate changes; dynamic land degradation; ArcGIS model builder; remote sensing; Oued el-Hai; Eastern Algeria; soil water erosion; USLE; GIS; watershed; vulnerability; downscaling; soil moisture; AMSR-E; random forest; North China; hyperspectral satellite data; soil organic matter; spectral transformation; spectral analysis; spectral index; quantile regression forests; random forests; geostatistics; machine learning; soil organic matter; prediction uncertainty; unmanned aerial vehicle hyperspectral image; fine classification of crops; characteristic transform; random forest; land surface temperature; downscaling; DisTrad; evapotranspiration; Landsat 8; MODIS; linear regression; thermal sensors; temporal resolution; spatial resolution; soil fertility modelling; GIS; ordinary kriging; cLHS; S2A image; drylands; Geographical Information System (GIS); spatial interpolation; SPT N; plasticity index; soil maps; time series; Sentinel-1; Sentinel-2; random forest; feature-level fusion; LiDAR; full waveform; decision tree; accuracy; gully erosion; hybrid machine learning; frequency ratio; Mediterranean area