4.7 Article

Digital mapping of soil organic carbon density using newly developed bare soil spectral indices and deep neural network

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Agronomy

An enhanced spatiotemporal fusion method - Implications for DNN based time-series LAI estimation by using Sentinel-2 and MODIS

Yan Li et al.

Summary: The monitoring of crop leaf area index is crucial for yield estimation and agriculture policy development. The EFF method proposed in this study effectively generates time-series synthetic images for real-time or post-growth applications.

FIELD CROPS RESEARCH (2022)

Article Computer Science, Interdisciplinary Applications

A robust methodology for optimizing the topology and the learning parameters of an ANN for accurate predictions of laser-cut edges surface roughness

John D. Kechagias et al.

Summary: This study optimized the Feed-Forward and Backpropagation Artificial Neural Networks (FFBP-ANN) using Taguchi Design of Experiments, reducing the combinations from 81 to 9. The optimized FFBP-ANN successfully predicted the surface roughness in different cut depths during laser cutting of thin thermoplastic plates.

SIMULATION MODELLING PRACTICE AND THEORY (2022)

Article Green & Sustainable Science & Technology

A framework based on multivariate distribution-based virtual sample generation and DNN for predicting water quality with small data

Ali El Bilali et al.

Summary: This study develops a novel framework using multivariate distributions to generate virtual samples, allowing for the application of deep neural networks (DNN) in predicting water quality with small datasets. The framework improves model performance and is useful for managing water quality in poorly monitored areas.

JOURNAL OF CLEANER PRODUCTION (2022)

Article Agronomy

Estimation of daily maize transpiration using support vector machines, extreme gradient boosting, artificial and deep neural networks models

Junliang Fan et al.

Summary: Accurate estimation of plant transpiration (T) is crucial for agricultural production, and this study investigated the use of machine learning models to estimate daily T of summer maize. Incorporating soil water content and leaf area index variables improved model performance, with the deep neural network (DNN) model slightly outperforming others.

AGRICULTURAL WATER MANAGEMENT (2021)

Article Geosciences, Multidisciplinary

Scale- and location-specific multivariate controls of topsoil organic carbon density depend on landform heterogeneity

Hongfen Zhu et al.

Summary: The study found that variations in soil organic carbon density and its scale-location specific controls were associated with landform heterogeneity. Wavelet methods outperformed traditional correlation analyses in untangling the controls of multivariate factors on soil organic carbon density variation at different locations and scales.

CATENA (2021)

Article Biodiversity Conservation

Estimating the spatial distribution of soil total arsenic in the suspected contaminated area using UAV-Borne hyperspectral imagery and deep learning

Lifei Wei et al.

Summary: The study successfully utilized UAV-borne hyperspectral data and deep neural networks to establish a model for estimating the total arsenic content and spatial distribution in soil, achieving good results in field experiments.

ECOLOGICAL INDICATORS (2021)

Article Soil Science

Clay content prediction using spectra data collected from the ground to space platforms in a smallholder tropical area

Henrique Bellinaso et al.

Summary: Proximal and remote sensors are important sources of soil spectral information, and this study explored clay content prediction at different spectral acquisition levels. Results showed that local spectral libraries performed well with FieldSpec 3 and AISA-FENIX sensors, while regional spectral libraries had poor prediction results.

GEODERMA (2021)

Article Soil Science

A regional-scale hyperspectral prediction model of soil organic carbon considering geomorphic features

Yilin Bao et al.

Summary: The study aimed to improve SOC prediction accuracy by using satellite hyperspectral image data and ancillary variables. Results showed that considering soil stratification strategy and ancillary variables significantly improved model accuracy.

GEODERMA (2021)

Article Environmental Sciences

Soil variability and quantification based on Sentinel-2 and Landsat-8 bare soil images: A comparison

Nelida Elizabet Quinonez Silvero et al.

Summary: This study evaluated the influence of satellite images at different resolutions on soil variability representation, bare soil areas percentage, and spatial predictions of soil properties in southeastern Brazil. The results indicate that bare soil images obtained by combining Landsat-8 and Sentinel-2 images are more important for soil mapping than spatial or spectral resolutions.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Soil Science

Semi-supervised DNN regression on airborne hyperspectral imagery for improved spatial soil properties prediction

Depin Ou et al.

Summary: This paper proposes a novel regression model for estimating the concentrations of soil organic matter and heavy metals, achieving good performance in experiments. The study also reveals the impact of snowmelt, frozen soil melting, and surface rainfall on the transport of soil components.

GEODERMA (2021)

Article Automation & Control Systems

Comparing CalReg performance with other multivariate methods for estimating selected soil properties from Moroccan agricultural regions using NIR spectroscopy

Rabie Reda et al.

Summary: CalReg model outperformed other tested models in predicting certain soil properties, MBL performed the best for other properties, while BPNN showed superior performance in yet another set of properties. The results suggest that CalReg helps improve the accuracy of soil property prediction, showcasing potential for accurately determining selected soil properties in the laboratory when combined with NIRS.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2021)

Article Environmental Sciences

A spatial assessment of mercury content in the European Union topsoil

Cristiano Ballabio et al.

Summary: Mapping of surface soil mercury concentrations at continental scale using Deep Neural Network models revealed an increase in mercury concentrations with latitude and altitude in European soils. The study found correlations between soil mercury concentrations and vegetation activity, NDVI, and soil organic carbon content, indicating the importance of atmospheric uptake by plants and soil organic matter on mercury distribution. Additionally, the research identified hotspots of mercury contamination, with some associated with mining areas and others potentially related to unmined geological mercury or industrial pollution.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Soil Science

Mapping soil organic carbon stock by hyperspectral and time-series multispectral remote sensing images in low-relief agricultural areas

Long Guo et al.

Summary: High-precision digital soil organic carbon (SOC) stocks mapping plays a crucial role in agricultural production management and global carbon cycle. This study successfully predicted SOC stock, SOC, and soil bulk density through hyperspectral and time-series multispectral remote sensing images, with the extreme learning machine (ELM) model outperforming the partial least square regression (PLSR) model. The combination of Sentinel 2 images and ELM achieved the best prediction results for soil properties in low relief farmland regions. This mapping strategy using time-series multispectral remote sensing images provides valuable information for agricultural management and carbon cycle research.

GEODERMA (2021)

Article Plant Sciences

Estimating leaf area index using unmanned aerial vehicle data: shallow vs. deep machine learning algorithms

Shuaibing Liu et al.

Summary: Our research aims to determine the contribution of multimodal data to LAI and propose a framework for estimating LAI based on remote-sensing data; evaluate the robustness and adaptability of an LAI estimation model that uses multimodal data fusion and deep neural networks (DNNs) in single- and whole growth stages; and explore how soil background and maize tasseling affect LAI estimation. Using low-cost UAVs and DNNs, multimodal data fusion accurately and reliably estimates LAI for crops, which is valuable for high-throughput phenotyping and high-spatial precision farmland management.

PLANT PHYSIOLOGY (2021)

Article Environmental Sciences

The application of proximal visible and near-infrared spectroscopy to estimate soil organic matter on the Triffa Plain of Morocco

Ayoub Lazaar et al.

INTERNATIONAL SOIL AND WATER CONSERVATION RESEARCH (2020)

Article Soil Science

Pedometrics timeline

Alex McBratney et al.

GEODERMA (2019)

Article Geochemistry & Geophysics

Imaging Spectroscopy for Soil Mapping and Monitoring

S. Chabrillat et al.

SURVEYS IN GEOPHYSICS (2019)

Article Soil Science

Digital mapping of soil carbon fractions with machine learning

Hamza Keskin et al.

GEODERMA (2019)

Review Instruments & Instrumentation

Proximal and remote sensing techniques for mapping of soil contamination with heavy metals

Tiezhu Shi et al.

APPLIED SPECTROSCOPY REVIEWS (2018)

Article Geography, Physical

Extracting leaf area index using viewing geometry effects-A new perspective on high-resolution unmanned aerial system photography

Lukas Roth et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2018)

Review Green & Sustainable Science & Technology

Estimation of renewable energy and built environment-related variables using neural networks - A review

Eugenio Rodrigues et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Article Environmental Sciences

Soil organic carbon and texture retrieving and mapping using proximal, airborne and Sentinel-2 spectral imaging

Asa Gholizadeh et al.

REMOTE SENSING OF ENVIRONMENT (2018)

Article Geosciences, Multidisciplinary

A global spectral library to characterize the world's soil

R. A. Viscarra Rossel et al.

EARTH-SCIENCE REVIEWS (2016)

Article Engineering, Electrical & Electronic

Characterization of Soil Erosion Indicators Using Hyperspectral Data From a Mediterranean Rainfed Cultivated Region

Thomas Schmid et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2016)

Article Environmental Sciences

Estimation of crop LAI using hyperspectral vegetation indices and a hybrid inversion method

Liang Liang et al.

REMOTE SENSING OF ENVIRONMENT (2015)

Article Soil Science

Comparing geospatial techniques to predict SOC stocks

Yaolin Liu et al.

SOIL & TILLAGE RESEARCH (2015)

Article Environmental Sciences

On the Synergy of Airborne GNSS-R and Landsat 8 for Soil Moisture Estimation

Nilda Sanchez et al.

REMOTE SENSING (2015)

Article Engineering, Environmental

Monitoring Arsenic Contamination in Agricultural Soils with Reflectance Spectroscopy of Rice Plants

Tiezhu Shi et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2014)

Article Soil Science

Visible-Near Infrared Spectra as a Proxy for Topsoil Texture and Glacial Boundaries

Maria Knadel et al.

SOIL SCIENCE SOCIETY OF AMERICA JOURNAL (2013)

Article Automation & Control Systems

Hybrid GA/SIMPLS as alternative regression model in dam deformation analysis

Chang Xu et al.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2012)

Article Soil Science

On the soil information content of visible-near infrared reflectance spectra

R. A. Viscarra Rossel et al.

EUROPEAN JOURNAL OF SOIL SCIENCE (2011)

Article Geography, Physical

An investigation into robust spectral indices for leaf chlorophyll estimation

Russell Main et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2011)

Article Soil Science

Predicting the Spatial Variation of the Soil Organic Carbon Pool at a Regional Scale

Umakant Mishra et al.

SOIL SCIENCE SOCIETY OF AMERICA JOURNAL (2010)

Article Geography

A Top-Down Approach to the State Factor Paradigm for Use in Macroscale Soil Analysis

Peter Scull

ANNALS OF THE ASSOCIATION OF AMERICAN GEOGRAPHERS (2010)

Article Computer Science, Artificial Intelligence

A fast learning algorithm for deep belief nets

Geoffrey E. Hinton et al.

NEURAL COMPUTATION (2006)

Article Soil Science

Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties

CW Chang et al.

SOIL SCIENCE SOCIETY OF AMERICA JOURNAL (2001)