Article
Soil Science
Wanderson De Sousa Mendes, Jose A. M. Dematte, Budiman Minasny, Nelida E. Q. Silvero, Benito R. Bonfatti, Jose Lucas Safanelli, Rodnei Rizzo, Antonio Carlos Saraiva Da Costa
Summary: Free iron content is an important indicator in tropical soils, and this study successfully developed a mapping strategy for predicting free iron distribution using remote sensing data, digital soil mapping, and machine learning algorithms.
SOIL & TILLAGE RESEARCH
(2022)
Article
Soil Science
Alexandre M. J. -C. Wadoux, Dick J. Brus
Summary: The study suggests that comparison of sampling designs for mapping should be based on the sampling distribution of map quality indices. In two different case studies, the performance of simple random sampling and conditioned Latin hypercube sampling showed large variations and significant overlaps at different sample sizes.
EUROPEAN JOURNAL OF SOIL SCIENCE
(2021)
Article
Forestry
Taciara Zborowski Horst-Heinen, Ricardo Simao Diniz Dalmolin, Alexandre ten Caten, Jean Michel Moura-Bueno, Sabine Grunwald, Fabricio de Araujo Pedron, Miriam Fernanda Rodrigues, Nicolas Augusto Rosin, Daniely Vaz da Silva-Sangoi
Summary: This study aimed to predict soil depth (SoD) and tree height in a complex landscape using digital soil mapping (DSM) and random forest (RF) models. Spatial data on SoD and topographic attributes were found to be crucial for accurately predicting tree height, highlighting the importance of localized predictions for effective silviculture practices.
FOREST ECOLOGY AND MANAGEMENT
(2021)
Article
Soil Science
Nicolas Augusto Rosin, Jose A. M. Dematte, Raul Roberto Poppiel, Nelida E. Q. Silvero, Heidy S. Rodriguez-Albarracin, Jorge Tadeu Fim Rosas, Lucas Tadeu Greschuk, Henrique Bellinaso, Budiman Minasny, Cecile Gomez, Jose Marques Junior, Kathleen Fernandes
Summary: Minerals are crucial for soil functions and addressing global issues. Soil spectroscopy is a useful tool to measure mineral abundance. This study used spectral data and digital soil mapping techniques to estimate the abundance of minerals in Brazil. The predictions were validated and found to be accurate, revealing the spatial distribution of mineral abundances at a finer resolution than existing maps.
Article
Environmental Sciences
Maria Eliza Turek, Laura Poggio, Niels H. Batjes, Robson Andre Armindo, Quirijn de Jong van Lier, Luis de Sousa, Gerard B. M. Heuvelink
Summary: The development of point-based global maps of soil water retention improves the availability and quality of soil data, compared to traditional map-based approaches. By combining measured and predicted data with environmental variables, this study demonstrates the superior performance of the point-based mapping approach.
INTERNATIONAL SOIL AND WATER CONSERVATION RESEARCH
(2023)
Article
Soil Science
Qingliang Li, Cheng Zhang, Wei Shangguan, Lu Li, Yongjiu Dai
Summary: Accurate mapping of soil texture is crucial for agricultural development and environmental activities. This study proposes a novel soil texture prediction model (LGD-LSTM) that utilizes multiple inputs and long short-term memory models to enhance prediction accuracy, outperforming other digital soil mapping methods.
Article
Soil Science
Kamal Nabiollahi, Ruhollah Taghizadeh-Mehrjardi, Aram Shahabi, Brandon Heung, Alireza Amirian-Chakan, Masoud Davari, Thomas Scholten
Summary: In a study conducted in Kurdistan Province, Iran, a combination of random forests and covariate data was used to assess the spatial variability of salinity and sodicity in agricultural salt-affected land. The results showed that optimization algorithms helped improve the accuracy of predictions, and identified groundwater table, categorical maps, salinity index, and multi-resolution ridge top flatness as important covariates for predicting soil salinity and sodicity.
Article
Soil Science
Fellipe A. O. Mello, Jose A. M. Dematte, Rodnei Rizzo, Andre C. Dotto, Raul R. Poppiel, Wanderson de S. Mendes, Clecia C. B. Guimaraes
Summary: Studies on soil maps using digital mapping techniques, considering drainage network info, evaluate its contribution to predicting soil classes. By calibrating models and cross-validation to optimize model selection, the performance of the models was validated.
Article
Agriculture, Multidisciplinary
Huan Zhang, Dengfeng Wang, Baowei Su, Shuangshuang Shao, Jie Yang, Manman Fan, Jingtao Wu, Chao Gao
Summary: This study found that low-yield paddy soils in southern China have low levels of soil organic carbon, alkaline hydrolyzable nitrogen, and available potassium, but high levels of available phosphorus. The use of double- and triple-cropping systems can effectively improve soil nutrient status, enhance the organic carbon pool, and increase rice production.
AGRICULTURE ECOSYSTEMS & ENVIRONMENT
(2021)
Article
Geosciences, Multidisciplinary
Gerard B. M. Heuvelink, Richard Webster
Summary: Pedologists traditionally mapped soil by drawing boundaries, but the introduction of geostatistics and ordinary kriging in the 1980s revolutionized soil mapping. Machine learning techniques have also been adopted, but they lack transparency and spatial correlation considerations. Spatial statisticians and pedometricians have important roles in incorporating uncertainty and communicating it to end users.
SPATIAL STATISTICS
(2022)
Article
Soil Science
Stephan van der Westhuizen, Gerard B. M. Heuvelink, David P. Hofmeyr
Summary: In digital soil mapping, traditional univariate methods neglect the dependence structure between soil properties, while multivariate machine learning models can capture complex non-linear relationships and maintain the dependence structure. This study compares the performance of a multivariate random forest model with two separate univariate random forest models, and finds that the multivariate model outperforms in maintaining the dependence structure and producing more realistic results.
Article
Environmental Sciences
Ruhollah Taghizadeh-Mehrjardi, Hassan Fathizad, Mohammad Ali Hakimzadeh Ardakani, Hamid Sodaiezadeh, Ruth Kerry, Brandon Heung, Thomas Scholten
Summary: This study aimed to predict the spatial distribution of absorbable heavy metals in arid regions of Iran from 1986 to 2016 using a random forest model, with successful predictions for Fe, Mn, Ni, Pb, and Zn. Results showed significant increases in heavy metal distribution over time, providing valuable insights for developing appropriate management strategies.
Article
Soil Science
Mei-Wei Zhang, Chenkai Hao, Xiaoqing Wang, Xiao-Lin Sun
Summary: The generalized linear geostatistical model (GLGM) is a formal approach for regression kriging that shows promise for digital soil mapping (DSM). This study evaluates the use of GLGM for mapping soil organic matter at a regional scale, and compares it with other commonly used approaches. Results suggest that GLGM generally improves the accuracy of DSM, particularly with larger sample sizes, although the improvement is not significant. The success of GLGM modeling and prediction is highly influenced by sampling densities.
Article
Environmental Sciences
Xibo Xu, Zeqiang Wang, Xiaoning Song, Wenjie Zhan, Shuting Yang
Summary: The selection of predictor variables is crucial in building a digital mapping model for potentially toxic elements (PTEs) in soil. Traditionally, spatial and spectral parameters have been used as predictor variables, but the temporal dimension is often overlooked. This study demonstrates the value of incorporating temporal indices in the model, leading to significant performance improvements. The temporal-spatial-spectral covariate combinations used in a random forest (RF) algorithm achieve satisfactory mapping accuracy and outperform other methods.
ENVIRONMENTAL RESEARCH
(2024)
Article
Environmental Sciences
Hua Jin, Xuefeng Xie, Lijie Pu, Zhenyi Jia, Fei Xu
Summary: This study accurately predicts the soil organic matter (SOM) content in a dryland agroecosystem by collecting soil samples and using machine learning models. The random forest model is determined as the optimal model. The study identifies alkali-hydrolyzable nitrogen, available potassium, mean annual precipitation, and pH as the main controlling factors affecting the spatial distribution of SOM.
Article
Environmental Sciences
Lais L. Silva, Marina M. Feitosa, Emerson F. Vilela, Guilherme Lopes, Luiz R. G. Guilherme, Yuri L. Zinn
Summary: High levels of arsenic were found in soils developed from ultramafic rocks in Brazil, but the arsenic was mainly contained in resistant phases and bound to secondary iron oxides. The availability of arsenic varied among soils, with some soils showing low availability and others showing high availability. Generally, the high arsenic contents in these soils do not raise immediate concerns, but the release of arsenic in groundwater and surface water deserves further investigation.
ENVIRONMENTAL RESEARCH
(2023)
Article
Environmental Sciences
Lucas Benedet, Sergio Henrique Godinho Silva, Marcelo Mancini, Renata Andrade, Francisco Helcio Canuto Amaral, Geraldo Janio Lima, Marco Aurelio Carbone Carneiro, Nilton Curi
Summary: Ca and Mg are important elements in lime, and their accurate measurement is crucial to assess its quality. Proximal sensors can provide a rapid and easy way to determine the Ca and Mg contents without producing chemical waste. Quality control of lime is important for its industrial and agricultural applications.
ENVIRONMENTAL RESEARCH
(2023)
Article
Geochemistry & Geophysics
Sergio Henrique Godinho Silva, Diego Ribeiro, Thais Santos Branco Dijair, Fernanda Magno Silva, Anita Fernanda dos Santos Teixeira, Renata Andrade, Marcelo Mancini, Luiz Roberto Guimaraes Guilherme, Nilton Curi
Summary: This study aims to evaluate the chemical composition of different quartz varieties using a portable X-ray fluorescence (pXRF) spectrometer and relate them to soil attributes. Hyaline quartz had the highest SiO2 content and the lowest contents of other elements. Random Forest algorithm identified SiO2, oxides, chlorine, sulfur, phosphorus pentoxide, and potassium oxide as the main components for discriminating quartz varieties. pXRF provided enhanced information on the chemical characterization of quartz varieties without generating chemical pollutants.
Article
Food Science & Technology
Maila Adriely Silva, Gustavo Ferreira de Sousa, Gary Banuelos, Douglas Amaral, Patrick H. Brown, Luiz Roberto Guimaraes Guilherme
Summary: This study aimed to evaluate the effect of different selenium application methods (soil or foliar) and sources (organic or inorganic) on the total selenium content and speciation in selenium-enriched soybean grains. The results showed that all treatments with inorganic selenium increased the selenium content in grains compared to the control. More than 80% of the total selenium was present as selenomethionine (SeMet), and the speciation was influenced by the selenium source and application method. The treatments using inorganic selenium, applied via soil or foliar, produced the highest content of SeMet in soybean grains. Finally, the preservation of selenium species in products derived from soybean grains should be evaluated.
Article
Food Science & Technology
Patriciani Estela Cipriano, Rodrigo Fonseca da Silva, Cynthia de Oliveira, Alexandre Boari de Lima, Fabio Aurelio Dias Martins, Gizele Celante, Alcindo Aparecido dos Santos, Marcos Vinicio Lopes Rodrigues Archilha, Marcos Felipe Pinatto Botelho, Valdemar Faquin, Luiz Roberto Guimaraes Guilherme
Summary: Agronomic biofortification with selenium can effectively increase the nutritional intake and grain yield of sorghum. Sodium selenate is more efficient compared to organoselenium compounds, but acetylselenide has a positive effect on the antioxidant system.
Article
Plant Sciences
Maila Adriely Silva, Gustavo Ferreira de Sousa, Gustavo Avelar Zorgdrager Van Opbergen, Guilherme Gerrit Avelar Zorgdrager Van Opbergen, Ana Paula Branco Corguinha, Jean Michel Moura Bueno, Gustavo Brunetto, Jose Marcos Leite, Alcindo Aparecido dos Santos, Guilherme Lopes, Luiz Roberto Guimaraes Guilherme
Summary: This study investigated the effects of selenium foliar application combined with a multi-nutrient fertilizer on soybean. The results showed that grain yield of soybean increased with the application of multi-nutrient fertilizer, while selenium rates linearly increased selenium contents up to 80 g Se ha(-1), regardless of the use of multi-nutrient fertilizer. The two genotypes (58I60 Lanca and M5917) had critical thresholds of 1.0 and 3.0 mg kg(-1) for grain selenium content, respectively. Selenium application promoted higher contents of K, P, and S in grains of genotype Lanca and higher contents of Mn and Fe in grains of genotype M5917. The findings highlight the importance of considering different fertilization strategies and genotypic variations when assessing the effects of selenium on soybean yield and grain quality.
Article
Environmental Sciences
Rafaella T. Silva de Sa, Marcelo Tesser Antunes Prianti, Renata Andrade, Aline Oliveira Silva, Eder Rodrigues Batista, Jesse Valentim dos Santos, Fernanda Magno Silva, Marco Aurelio Carbone Carneiro, Luiz Roberto Guimaraes Guilherme, Somsubhra Chakraborty, David C. Weindorf, Nilton Curi, Sergio Henrique Godinho Silva, Bruno Teixeira Ribeiro
Summary: After a dam failure similar to Funda in Brazil, a large amount of iron-rich tailings were released, impacting a wide area. It is necessary to characterize and monitor these tailings for agronomic and environmental purposes. This study used portable X-ray fluorescence (pXRF) spectrometry, a pocket-sized color sensor, and a benchtop magnetic susceptibilimeter, combined with other sensors, to rapidly and accurately characterize the iron-rich tailings and predict important soil agronomic properties and concentrations of potentially toxic elements.
ENVIRONMENTAL RESEARCH
(2023)
Article
Plant Sciences
Jucelino de Sousa Lima, Otavio Vitor Souza Andrade, Leonidas Canuto dos Santos, Everton Geraldo de Morais, Gabryel Silva Martins, Yhan S. Mutz, Vitor L. Nascimento, Paulo Eduardo Ribeiro Marchiori, Guilherme Lopes, Luiz Roberto Guimaraes Guilherme
Summary: Water deficit inhibits plant growth and leads to overproduction of reactive oxygen species (ROS), causing oxidative stress. Iodine (I) has been shown to enhance the antioxidant defense system and improve photosynthesis under adverse conditions. In this study, soybean plants exposed to potassium iodide (KI) concentrations of 10 and 20 .mol L-1 showed increased biomass, improved gas exchange, and reduced lipid peroxidation under water deficit. However, higher KI concentrations negatively affected photosynthetic efficiency, biomass accumulation, and partition under well-irrigated conditions.
Article
Plant Sciences
Gustavo Ferreira de Sousa, Maila Adriely Silva, Mariana Rocha de Carvalho, Everton Geraldo de Morais, Pedro Antonio Namorato Benevenute, Gustavo Avelar Zorgdrager Van Opbergen, Guilherme Gerrit Avelar Zorgdrager Van Opbergen, Luiz Roberto Guimaraes Guilherme
Summary: This study aimed to investigate the role of Se supply in improving osmotic stress tolerance in coffee seedlings while also evaluating the best timing for Se application. Results demonstrated that osmotic stress promoted mild stress in the coffee plants and led to starch degradation. Seedlings that received foliar Se application 8 days before the stress exhibited higher antioxidant enzyme activity compared to the control group.
Article
Soil Science
Alvaro Jose Gomes de Faria, Sergio Henrique Godinho Silva, Luiza Carvalho Alvarenga Lima, Renata Andrade, Livia Botelho, Leonidas Carrijo Azevedo Melo, Luiz Roberto Guimaraes Guilherme, Nilton Curi
Summary: By using portable X-ray fluorescence (pXRF), the results of the USEPA 3051a method for chemical elements can be accurately predicted, saving time and cost, and enabling large-scale geochemical characterization of tropical soils in an environmentally friendly way.
Article
Soil Science
Devison Souza Peixoto, Sergio Henrique Godinho Silva, Silvino Guimaraes Moreira, Alessandro Alvarenga Pereira da Silva, Thayna Pereira Azevedo Chiarini, Lucas de Castro Moreira da Silva, Nilton Curi, Bruno Montoani Silva
Summary: This study evaluated the performance of four machine learning algorithms in diagnosing the state of soil compaction, with decision tree algorithms (CART and RF) outperforming ANN and SVM. The diagnosis accuracy reached 90%, Kappa index was 0.76, and sensitivity was 0.83. Therefore, machine learning algorithms proved to be efficient tools in diagnosing soil compaction in continuous no-tillage.