Instance selection in digital soil mapping: a study case in Rio Grande do Sul, Brazil

Giasson, Élvio; Caten, Alexandre ten; Bagatini, Tatiane; Bonfatti, Benito Roberto

doi:10.1590/0103-8478cr20140694

Cited by 11 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…slope, topographic wetness index, curvatures, etc. ), to spatialize soils information (Adhikari et al, 2014;Giasson et al, 2015;Menezes et al, 2014;Silva et al, 2016a;TaghizadehMehrjardi et al, 2015). However, when working in smaller areas, mainly in developing countries, it is common to face difficulties in obtaining data with high spatial resolution, which tends to make the use of these variables unfeasible.…”

Section: Introductionmentioning

confidence: 99%

Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

et al. 2017

View full text Add to dashboard Cite

Determination of soil properties helps in the correct management of soil fertility. The portable X-ray fluorescence spectrometer (pXRF) has been recently adopted to determine total chemical element contents in soils, allowing soil property inferences. However, these studies are still scarce in Brazil and other countries. The objectives of this work were to predict soil properties using pXRF data, comparing stepwise multiple linear regression (SMLR) and random forest (RF) methods, as well as mapping and validating soil properties. 120 soil samples were collected at three depths and submitted to laboratory analyses. pXRF was used in the samples and total element contents were determined. From pXRF data, SMLR and RF were used to predict soil laboratory results, reflecting soil properties, and the models were validated. The best method was used to spatialize soil properties. Using SMLR, models had high values of R² (≥0.8), however the highest accuracy was obtained in RF modeling. Exchangeable Ca, Al, Mg, potential and effective cation exchange capacity, soil organic matter, pH, and base saturation had adequate adjustment and accurate predictions with RF. Eight out of the 10 soil properties predicted by RF using pXRF data had CaO as the most important variable helping predictions, followed by P 2 O 5 , Zn and Cr. Maps generated using RF from pXRF data had high accuracy for six soil properties, reaching R 2 up to 0.83. pXRF in association with RF can be used to predict soil properties with high accuracy at low cost and time, besides providing variables aiding digital soil mapping.Index terms: Soil analyses; spatial prediction; proximal sensor. RESUMOA determinação de atributos do solo auxilia no correto manejo da sua fertilidade. O equipamento portátil de fluorescência de raios-X (pXRF) foi recentemente adotado para determinar o teor total de elementos químicos em solos, permitindo inferências sobre atributos do solo. No entanto, esses estudos ainda são escassos no Brasil e em outros países. Os objetivos deste trabalho foram prever atributos do solo a partir de dados do pXRF, comparando-se os métodos de regressão linear múltipla stepwise (SMLR) e de random forest (RF), além de mapear e validar atributos do solo. 120 amostras de solo foram coletadas em três profundidades e submetidas a análises laboratoriais. Utilizou-se o pXRF para leitura das amostras e determinou-se o teor total de elementos. A partir dos dados do pXRF, foram utilizadas SMLR e RF para predizer resultados laboratoriais, que refletem atributos do solo, e os modelos foram validados. O melhor método foi utilizado para espacializar os atributos do solo. Utilizando SMLR, os modelos apresentaram valores elevados de R² (≥0,8), porém maior acurácia foi obtida na modelagem com RF. A capacidade de troca de cátions potencial e efetiva, matéria orgânica do solo, pH, saturação por bases e teores trocáveis de Ca, Al e Mg apresentaram ajustes adequados e predições acuradas com RF. Dos dez atributos do solo preditos por RF a partir de dados do pXRF, sete apr...

show abstract

Section: Introductionmentioning

confidence: 99%

Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

et al. 2017

View full text Add to dashboard Cite

show abstract

“…De modo geral, a reprodutibilidade do mapa convencional de solos (Tabela 4) com os dados coletados apenas nos pixels dos perfis de solos alcançou valores próximos ao valor médio de 60% observado na literatura em estudos com outras estratégias de amostragem utilizada no mapeamento digital de solos (Höfig et al, 2014;Giasson et al, 2015;Bagatini et al, 2016;Dias et al, 2016;Pelegrino et al, 2016). Vale destacar que em ambas as áreas de estudo apenas duas unidades representam mais de 75% da composição dos respectivos mapas de solos, sendo estas as mais importantes na predição e as quais apresentaram maior concordância com os mapas legados utilizados na validação.…”

Section: /9unclassified

Índice de área foliar residual como estratégia para manejo de pasto: estrutura do capim Tanzânia

Lemos

Ruggieri

Silva

et al. 2019

Agraria

View full text Add to dashboard Cite

AGRONOMIA (AGRONOMY) RESUMO: Os estudos de mapeamento digital de classes de solos (MDS) têm utilizado mapas legados como principal fonte de informação para calibração dos modelos preditores. Entretanto, são necessárias novas abordagem com técnicas que permitam o uso de informações contidas em perfis de solos georreferenciados, permitindo a aplicação do MDS em áreas amostradas que não disponibilizem de mapas convencionais de solos. O objetivo deste estudo foi avaliar o desempenho na predição de ocorrência de solos de amostras coletadas em pixels de perfis de solos georreferenciados e em pixels coletados em buffers com raio de 50, 100, 150, 200 e 250 m dos perfis de solos nas bacias dos rios Lajeado Grande e Santo Cristo. As duas áreas possuem dados de levantamento de solos publicados em escala 1:50.000. Para predição da ocorrência das classes de solos foram utilizadas dez variáveis preditoras geradas a partir de um modelo digital de elevação com resolução espacial de 30 m. Para a predição foi utilizado o algoritmo Random Forest. Os mapas preditos foram avaliados quanto à exatidão em relação aos perfis de solos e quanto a reprodutibilidade dos mapas convencionais. A utilização dos pixels amostrais coletados nos buffers não alterou de forma expressiva a acurácia geral dos mapas preditos na bacia do rio Lajeado Grande, mas permitiu um ganho de 15,6% de exatidão na bacia do rio Santo Cristo. O uso apenas dos perfis georreferenciados resultou em mapas preditos com exatidão superior a 75% e concordância de reprodutibilidade igual ou superior a 67% em relação ao mapa convencional.

show abstract

“…A larger training dataset is often necessary in order to reduce error (Pal and Mather, 2003), and in this study, such information also brought stability to model errors in training data above 105 observations. However, it is important to highlight that the use of polygons and buffers could bring some uncertainty as regards the soil type, mainly closer to the boundaries or transition zones (Pelegrino et al, 2016;ten Caten et al, 2012;Giasson et al, 2015). Thus, the key point here is will the more accurate models deliver accurate soil maps in the digitally mapped area?…”

Section: Model Evaluationmentioning

confidence: 99%

Soil type spatial prediction from Random Forest: different training datasets, transferability, accuracy and uncertainty assessment

Machado

Silva

Curi

et al. 2019

Sci. agric. (Piracicaba, Braz.)

View full text Add to dashboard Cite

Different uses of soil legacy data such as training dataset as well as the selection of soil environmental covariables could drive the accuracy of machine learning techniques. Thus, this study evaluated the ability of the Random Forest algorithm to predict soil classes from different training datasets and extrapolate such information to a similar area. The following training datasets were extracted from legacy data: a) point data composed of 53 soil samples; b) 30 m buffer around the soil samples, and soil map polygons excluding: c) 20 m; and d) 30 m from the boundaries of polygons. These four datasets were submitted to principal component analysis (PCA) to reduce multidimensionality. Each dataset derived a new one. Different combinations of predictor variables were tested. A total of 52 models were evaluated by means of error of models, prediction uncertainty and external validation for overall accuracy and Kappa index. The best result was obtained by reducing the number of predictors with the PCA along with information from the buffer around the points. Although Random Forest has been considered a robust spatial predictor model, it was clear it is sensitive to different strategies of selecting training dataset. Effort was necessary to find the best training dataset for achieving a suitable level of accuracy of spatial prediction. To identify a specific dataset seems to be better than using a great number of variables or a large volume of training data. The efforts made allowed for the accurate acquisition of a mapped area 15.5 times larger than the reference area.

show abstract

Instance selection in digital soil mapping: a study case in Rio Grande do Sul, Brazil

Abstract: A critical issue in digital soil mapping (DSM) is the selection of data sampling method for model training. One emerging approach applies instance selection to reduce the size of the dataset by drawing only relevant samples in order to obtain a representative subset that is

Cited by 11 publications

References 9 publications

Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

Índice de área foliar residual como estratégia para manejo de pasto: estrutura do capim Tanzânia

Soil type spatial prediction from Random Forest: different training datasets, transferability, accuracy and uncertainty assessment

Contact Info

Product

Resources

About