Soil depth prediction by digital soil mapping and its impact in pine forestry productivity in South Brazil

Horst-Heinen, Taciara Zborowski; Dalmolin, Ricardo Simão Diniz; Caten, Alexandre ten; Moura-Bueno, Jean Michel; Grunwald, Sabine; Pedron, Fabrício de Araújo; Rodrigues, Miriam Fernanda; Rosin, Nícolas Augusto; Silva-Sangoi, Daniely Vaz da

doi:10.1016/j.foreco.2021.118983

Cited by 16 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the central part of predictions lied close to the observed values, in some cases, the model tended to underestimate soil depth of deep soils which could lead to misclassifications of areas as unproductive based on their depth (Figure 9). Taciara Zborowski et al (2021) working at landscape scale achieved similar results predicting soil depth using topographical information and tree-based models. Unlike our results, these authors concluded that overestimation occurred at locations with shallow soils.…”

Section: Resultsmentioning

confidence: 74%

“…Most of these studies relied on linear associations between interpolated ECa measurements and soil depth estimates, failing to account for nonlinear patterns of the data (Sudduth et al, 2010;Tol et al, 2013). Statistical learning techniques such as tree-based regression models offer an alternative to explore these kinds of relationships (James et al, 2017;Taciara Zborowski et al, 2021;Wadoux et al, 2020).…”

Section: Core Ideasmentioning

confidence: 99%

“…Understanding the spatial distribution of soil depth to a restrictive layer, such as a petrocalcic horizon, is important for proper land evaluation, use, and management (Boettinger et al, 1997;Domenech et al, 2017;Taciara Zborowski, et al, 2021). On a landscape scale, knowledge of soil depth distribution facilitates the creation of useful soil survey information, such as accurate soil map unit descriptions and delineations (Boettinger et al, 1997;Dharumarajan et al, 2020;McBratney et al, 2003;Taciara Zborowski, et al, 2021). The Argentinean pampas is a vast plain region of about 50 Mha, and it is considered one of the most suitable areas for grain crop production in the world (Satorre & Slafer, 1999).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mapping soil depth in southern pampas Argentina using ancillary data and statistical learning

Peralta

Alesso

Costa

et al. 2021

Soil Science Soc of Amer J

View full text Add to dashboard Cite

Restrictive layers such as hardpans limit the soil water and nutrients available for crops. In the southern Argentinean pampas, petrocalcic hardpans are found at variable depth within the field. Mapping the spatial distribution of depth to the petrocalcic hardpan is important for proper land evaluation, use, and management. Intensive grid sampling and spatial interpolation are labor-intensive and time-consuming mapping approaches for this soil property. In addition, the spatial distribution of this property is often difficult for interpolation techniques such as kriging. This study's objective was to evaluate the potential of soil electrical conductivity (ECa) and terrain attributes to map within-field spatial variation of soil depth using statistical learning techniques. Soil depth measurements up to 1-m depth were taken in eight fields at spatial sampling density ranging from 2 to 12 points ha -1 . Spatially dense data of elevation, terrain attributes, and ECa were migrated to soil depth sampling points and also spatially aggregated to include spatial information into the featured space. Then, random forest regression models were used to predict soil depth from colocated ECa and terrain data. Models were cross-validated using a k-fold approach using entire fields as folds. The overall model (using all data) resulted in out-of-the bag R 2 and RMSE of .66 and 22.8 cm respectively. Shallow (0-30 cm) and deep (0-90 cm) ECa values were the most important variables, accounting for variability at different ranges, but the importance varied between the soil types. These results suggested that field-scale ECa data and terrain attributes have potential to predict soil depth to hardpan. Further research is needed to improve the generalization of these models and improve the representation of spatial effects in order to implement site-specific management based on soil depth maps.

show abstract

Section: Resultsmentioning

confidence: 74%

Section: Core Ideasmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mapping soil depth in southern pampas Argentina using ancillary data and statistical learning

Peralta

Alesso

Costa

et al. 2021

Soil Science Soc of Amer J

View full text Add to dashboard Cite

show abstract

“…Ketebalan tanah merupakan salah satu karakteristik tanah yang penting. Informasi ketebalan tanah berkaitan dengan jasa ekosistem terutama pada aktivitas karbon tanah, suhu, dan air (Horst-Heinen et al, 2021), kesesuaian lahan dan pertumbuhan vegetasi (Chen et al, 2019), kondisi aliran permukaan (Han et al, 2018), dan kerawanan longsor (Ho et al, 2012;Kim et al, 2016) (Bostan et al, 2012;Lamichhane et al, 2019;Yang et al, 2019;John et al, 2022). Pendekatan dari dua metode ini cukup berbeda sehingga hasil pemetaan dapat memiliki perbedaan dalam konteks variasi spasial.…”

Section: Pendahuluanunclassified

Perbandingan Metode Multiple Linear Regression (Mlr) Dan Regression Kriging (Rk) Dalam Pemetaan Ketebalan Tanah Digital

Ramadhan

Samodra

Nugraha

et al. 2023

J. Tanah Sumberd. Lahan

View full text Add to dashboard Cite

Soil thickness has a significant influence on many of earth surface processes, and it can be mapped using various methods. Digital soil mapping can be used to estimate the spatial distribution of soil thickness and can estimate the uncertainty of the soil prediction map. Digital soil mapping using regression methods such as Multiple Linear Regression (MLR) and Regression Krigging (RK) was used to estimate soil thickness of the slope of Bener Reservoir. Bener Dam is a national strategic project which is built for irrigation to improve farming quantity. The aim of this research was to determine the spatial variation of the soil thickness at the slope of Bener Reservoir. The accuracy of MLR and RK were compared to select the best soil thickness prediction. There were 212 and 53 soil thickness samples from fieldwork which were used for data training and testing, respectively. There were 5 environmental variables such as elevation, distance from river, slope, plan curvature, and topographic wetness index. R programming language with gstat, krige, and stats Packages was employed for MLR and RK prediction. The result showed that KR is more accurate than MLR.

show abstract

“…Finally, the result is summarized with the mean of the model skill scores. In this work, we applied the 10-fold cross-validation, which has been used in DSM works and produced good results (Brus et al, 2011;Horst-Heinen et al, 2021;Loiseau et al, 2021).…”

Section: Soil Data Splitting (Cross-validation)mentioning

confidence: 99%

Remote sensing technologies for digital soil mapping: applications for agriculture and environmental planning

Mello¹

View full text Add to dashboard Cite

Remote sensing technologies for digital soil mapping: applications for agriculture and environmental planning / Fellipe Alcantara de Oliveira Mello. --Piracicaba, 2022. 105 p. Tese (Doutorado) --USP / Escola Superior de Agricultura "Luiz de Queiroz". 1. Mapeamento digital de solos 2. Sensoriamento remoto 3. Redes de drenagem 4. Solos hidromórficos I. Título DEDICATÓRIA À Ana, Nilton, Ivanilza e Luccas Por todo suporte, incentivo e apoio incondicional Dedico. 4 AGRADECIMENTOS Primeiramente agradeço a Deus pelas incontáveis bençãos que recebo em minha vida todos os dias. A fé depositada em Jesus Cristo me trouxe para o desafio da pós-graduação e me sustentou durante estes cinco anos e meio. Sem esta certeza não seria possível superar os obstáculos e por isso continuo dedicando minha fé naquele que fortalece. Todos os dias deste doutorado foram compartilhados com minha querida esposa Ana. Os sorrisos, lágrimas e ansiedades eram primeiro recebidos por ela. Sem seu suporte e apoio essa conquista não seria possível e, por isso, sou profundamente grato. Por meu pai Nilton que abriu mão de finais de semana para investir em meus estudos e sempre acreditou no meu potencial. A minha mãe Ivanilza que chorou quando saí de casa, mas que se orgulha muito dessa conquista. Sem vocês eu não estaria aqui. Ao meu irmão Luccas, agradeço por entender essa mudança, deixar de jogar basquete nos finais de semana e me apoiar nas lutas e dificuldades. Não seria o mesmo sem minha família. Agradeço a meu sogro e sogra, Nivaldo e Hilda, por me receberem como um filho desde 2017 e pela amizade e confiança. Também a Pedro, Sara e Taís por toda amizade e parceria durante uma fase tão importante em nossas vidas (casamentos, mudanças, sonhos...). Aos professores da ESALQ/USP de quem recebi ensinamentos e conhecimento incalculáveis. Ao Departamento de Ciência do Solo e do PPG de Solos e Nutrição de Plantas por toda estrutura e apoio necessários. Em especial ao professor e orientador José Alexandre Melo Demattê, que me recebeu para o mestrado e confiou em meu trabalho para o doutorado. A oportunidade e o crescimento pessoal e profissional adquiridos neste período são muito maiores do que poderia imaginar. Obrigado por todo suporte e parceria ao longo destes anos. Aos professores Tiago Osório Ferreira, Benito Roberto Bonfatti e Eliângela Benedet da Silva por todas as sugestões e correções na qualificação. Ao professor Pablo Vidal-Torrado e sua disciplina de Gênese e Classificação de Solos, que foi o diferencial para meu trabalho como pesquisador em pedologia. Ao professor Igo Fernando Lepsch, com o qual tive o prazer e honra de conviver e trabalhar no levantamento de solos.

show abstract

Soil depth prediction by digital soil mapping and its impact in pine forestry productivity in South Brazil

Cited by 16 publications

References 42 publications

Mapping soil depth in southern pampas Argentina using ancillary data and statistical learning

Mapping soil depth in southern pampas Argentina using ancillary data and statistical learning

Perbandingan Metode Multiple Linear Regression (Mlr) Dan Regression Kriging (Rk) Dalam Pemetaan Ketebalan Tanah Digital

Remote sensing technologies for digital soil mapping: applications for agriculture and environmental planning

Contact Info

Product

Resources

About