A5061651690- Soil Geostatistics and Mapping
- Geochemistry and Geologic Mapping
- Soil Carbon and Nitrogen Dynamics
- Soil and Land Suitability Analysis
- Soil erosion and sediment transport
- Mineral Processing and Grinding
- Soil Management and Crop Yield
- Spectroscopy and Chemometric Analyses
- Peatlands and Wetlands Ecology
- Remote Sensing in Agriculture
- Soil and Unsaturated Flow
- Growth and nutrition in plants
- Smart Agriculture and AI
- Remote Sensing and LiDAR Applications
- Soil Moisture and Remote Sensing
- Heavy metals in environment
- Genetics and Plant Breeding
- Geography and Environmental Studies
- Agricultural and Food Sciences
- Clay minerals and soil interactions
- Urban Heat Island Mitigation
- Image Processing and 3D Reconstruction
- Weed Control and Herbicide Applications
- Environmental and biological studies
- Forest Biomass Utilization and Management
Food and Agriculture Organization of the United Nations
2025
Leibniz Centre for Agricultural Landscape Research
2021-2023
Manaaki Whenua – Landcare Research
2023
Universidade de São Paulo
2017-2021
Forest Science and Research Institute
2019-2021
Secretaria de Agricultura e Abastecimento
2020
Universidade Federal do Piauí
2017-2018
Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, bottleneck its more widespread adoption the need establishing large reference datasets training machine learning (ML) models, which called spectral libraries (SSLs). Similarly, prediction capacity of new samples also subject number diversity types conditions represented in SSLs. To help bridge this gap enable hundreds stakeholders collect...
Abstract. The number of samples used in the calibration data set affects quality generated predictive models using visible, near and shortwave infrared (VIS–NIR–SWIR) spectroscopy for soil attributes. Recently, convolutional neural network (CNN) has been regarded as a highly accurate model predicting properties on large database. However, it not yet ascertained how sample size should be CNN to effective. This paper investigates effect training accuracy deep learning machine models. It aims...
The mapping of soil attributes provides support to agricultural planning and land use monitoring, which consequently aids the improvement quality food production. Landsat 5 Thematic Mapper (TM) images are often used estimate a given attribute (i.e., clay), but have potential model many other attributes, providing input for applications. In this paper, we aim evaluate Bare Soil Composite Image (BSCI) from state São Paulo, Brazil, calculated multi-temporal dataset, study its relationship with...
Abstract The Earth’s surface dynamics provide essential information for guiding environmental and agricultural policies. Uncovered unprotected surfaces experience several undesirable effects, which can affect soil ecosystem functions. We developed a technique to identify global bare areas their based on multitemporal remote sensing images aid the spatiotemporal evaluation of anthropic natural phenomena. its changes were recognized by Landsat image processing over time range 30 years using...
Soil mapping demands large-scale surveys that are costly and time consuming. It is necessary to identify strategies with reduced costs obtain detailed information for soil mapping. We aimed compare multispectral satellite image relief parameters the quantification of clay sand contents. The Temporal Synthetic Spectral (TESS) reflectance Image (SYSI) approaches were used characterize texture spectral signatures at level. samples collected (0–20 cm depth, 919 points) from an area 14,614 km2 in...
Soil organic carbon (SOC) stocks are a remarkable property for soil and environmental monitoring. The understanding of their dynamics in crop soils must go forward. objective this study was to determine the impact temporal controlling factors obtained by satellite images over SOC along depth, using machine learning algorithms. work carried out São Paulo state (Brazil) an area 2577 km2. We dataset boreholes with analyses from topsoil subsoil (0–100 cm). Additionally, remote sensing covariates...
The capacity of soil to sequester carbon (C) is a key process that promotes the reduction CO2 in atmosphere. Soils can absorb as much 20% anthropogenic emissions, which contribute mitigate climate change. This relies on organo-mineral association, includes different minerals, Fe and Al oxides, have critical organic (SOC) sorption surface. Based an equation potential C saturation deficit fine particles (<20 μm/silt clay fractions) for tropical regions, this study investigated SOC...
Abstract Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, bottleneck its more widespread adoption the need establishing large reference datasets training machine learning (ML) models, which called spectral libraries (SSLs). Similarly, prediction capacity of new samples also subject number diversity types conditions represented in SSLs. To help bridge this gap enable hundreds stakeholders collect...
This study evaluates the development and productivity of maize plants at different spatial arrangements under rainfed conditions in cerrado-caatinga (savannah) transition zone, where characterised as semiarid.The experimental plan was Randomised Blocks Design (RBD) with four replications.This 3×3 factorial design three types row spacing (0.35 m, 0.50 0.75 m) population density (50,000, 65,000 plants.ha - , 80,000 ).The hybrid 30F53YH recommended for region used this experiment.We collected...
Abstract. The number of samples used in the calibration dataset affects quality generated predictive models using visible, near and shortwave infrared (VIS-NIR-SWIR) spectroscopy for soil attributes. Recently, convolutional neural network (CNN) is regarded as a highly accurate model predicting properties on large database, however it has not been ascertained yet how sample size should be CNN to effective. This paper aims at providing an estimate much are needed improve performance...