Mapa digital de solos: uma proposta metodológica usando inferência fuzzy

Carvalho, Claudia Csekö Nolasco de; Franca-Rocha, Washington; Ucha, José Martin

doi:10.1590/s1415-43662009000100007

Cited by 15 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In DSM the automated quantitative and spatial prediction of soil properties and classes is treated and assisted by computational processing, through hardware and software appropriate or adapted (de Menezes and Ávila, 2005). Some Brazilian researchers using artificial intelligence, spectroscopy, geotechnologies, and geographic information systems are demonstrating the potential of these tools (Chagas et al, 2011; Loss et al, 2011; Coelho, 2010; López, 2009; Nolasco‐Carvalho et al, 2009; ten Caten et al, 2009; Sousa Junior and Demattê, 2008; Fiorio, 2002; Demattê et al, 2001).…”

Section: Digital Soil Mapping Prospects In Brazilmentioning

confidence: 99%

Soil Surveys in Brazil and Perspectives in Soil Digital Mapping

et al. 2015

View full text Add to dashboard Cite

In analyzing the evolution of pedologic mapping perspectives in Brazil, it is noteworthy that they are based firmly on geology and focused on soil aptitude for agricultural use. Mapping detail was improved between the decades of 1950 and 1980. The mapping initially concentrated in the Northeast and Southeast regions, shifting its orientation in recent decades with the opening of the Brazilian agricultural frontiers. Remote sensing, geographical information systems, and informatics allowed increased map detail and promoted technological changes in map production. This revolution provided the development of digital soil mapping (DSM) as a set of methods and techniques to automate the soil surveys in Brazil. Despite the technological advances, only 1% of the Brazilian territory has soil maps on the scale of 1:25,000. In 1990 for economical, technological, and methodological reasons there was a decrease in both surveying and detailing processes. In a response to this reality Brazil has used new software and technologies, as well as the accumulated knowledge, to increase technological development of soil surveys. The integration of existing techniques and data favor the faster construction of more detailed and more interactive soil maps for a larger parcel of the country. This perspective, as the former one, will require some modifications to the soil mapping both in the methodology and also in the approach.

show abstract

Section: Digital Soil Mapping Prospects In Brazilmentioning

confidence: 99%

Soil Surveys in Brazil and Perspectives in Soil Digital Mapping

et al. 2015

View full text Add to dashboard Cite

show abstract

“…In the evaluation of the maps produced by DSM, most authors take a single conventional soil map as reference, for a same legend (for example Chagas et al, 2011;Nolasco-Carvalho et al, 2009;Behrens et al, 2005;Demattê et al, 2004). However, conventional maps differ according to the soil scientist that constructed it, since their establishment includes both science and art (Soil Survey Staff, 1993).…”

Section: Introductionmentioning

confidence: 99%

Comparison between detailed digital and conventional soil maps of an area with complex geology

Filho¹,

Rizzo

Lepsch

et al. 2013

Rev. Bras. Ciênc. Solo

View full text Add to dashboard Cite

SUMMARYSince different pedologists will draw different soil maps of a same area, it is important to compare the differences between mapping by specialists and mapping techniques, as for example currently intensively discussed Digital Soil Mapping. Four detailed soil maps (scale 1:10.000) of a 182-ha sugarcane farm in the county of Rafard, São Paulo State, Brazil, were compared. The area has a large variation of soil formation factors. The maps were drawn independently by four soil scientists and compared with a fifth map obtained by a digital soil mapping technique. All pedologists were given the same set of information. As many field expeditions and soil pits as required by each surveyor were provided to define the mapping units (MUs). For the Digital Soil Map (DSM), spectral data were extracted from Landsat 5 Thematic Mapper (TM) imagery as well as six terrain attributes from the topographic map of the area. These data were summarized by principal component analysis to generate the map designs of groups through Fuzzy K-means clustering. Field observations were made to identify the soils in the MUs and classify them according to the Brazilian Soil Classification System (BSCS). To compare the conventional and digital (DSM) soil maps, they were crossed pairwise to generate confusion matrices that were mapped. The categorical analysis at each classification level of the BSCS showed that the agreement between the maps (1) Part of the Dissertation of the first author, submitted to the Escola Superior de Agricultura "Luiz de Queiroz" -ESALQ/USP.Received for publication on November 1st, 2012 and approved on July 11, 2013. (2 RESUMO: COMPARAÇÃO ENTRE MAPAS DE SOLOS DETALHADOS OBTIDOS PELOS MÉTODOS CONVENCIONAL E DIGITAL EM

show abstract

“…The soil mapping process requires the knowledge and experience of a senior pedologist for the stages of soil surveying, soil classification, and soil mapping (Kempen et al, 2012;Resende et al, 2014). For mapping soils, the pedologist makes use of environmental information, such as climate, lithology, vegetation, and landforms; analyses and interpretations of soil samples collected in the area of interest; and consideration of all elements involved in soil-landscape dynamics (Nolasco-Carvalho et al, 2009;Brady and Weil, 2013;Schaefer, 2013). Through a systematic analysis of field observation and supporting data during the mapping, the pedologist identifies the relationships between soils and landscape features and establishes the soil mapping unit boundaries to be drawn on the map (Nolasco-Carvalho et al, 2009;Brevik et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area

Meier

Souza

Francelino

et al. 2018

Rev. Bras. Ciênc. Solo

View full text Add to dashboard Cite

Increasingly, applications of machine learning techniques for digital soil mapping (DSM) are being used for different soil mapping purposes. Considering the variety of models available, it is important to know their performance in relation to soil data and environmental variables involved in soil mapping. This paper investigated the performance of eight machine learning algorithms for soil mapping in a tropical mountainous area of an official rural settlement in the Zona da Mata region in Brazil. Morphometric maps generated from a digital elevation model, together with Landsat-8 satellite imagery, and climatic maps, were among the set of covariates to be selected by the Recursive Feature Elimination algorithm to predict soil types using machine learning algorithms. Mapping performance was assessed using the confusion matrix, and the Z-test among the Kappa indexes of the matrices. In a conventional soil survey, the soils described and classified in the Brazilian System of Soil Classification [Argissolos Vermelho-Amarelos Distróficos-PVAd (Acrisols), Cambissolos Háplicos Tb Distróficos-CXbd (Cambisols), Gleissolos Háplicos Háplicos Tb Distróficos-GXbd (Gleysols), Latossolos Amarelos Distróficos-LAd (Xanthic Ferralsos), Latossolos Vermelho-Amarelos Distróficos-LVAd (Rhodic Ferralsols), and Neossolos Litólicos Distróficos-RLd (Neossols)] were grouped into composite mapping units (MU) using the conventional method. The eight algorithms showed similar performance without statistical difference (Kappa 0.42-0.48). The mapping of soils with varying slopes (LAd, LVAd, CXbd) showed lower accuracy, whereas soils on hydromorphic lowlands (GXbd) were classified more accurately. In map algebra, the result was rather satisfactory, with 63-67 % agreement between the conventional soil map and maps produced by machine learning. The areas with the largest disagreement in the DSM occurred in the LAd unit due to subtle color variation in the Latossolos mantle without a clear relation to any environmental variable, highlighting difficulties in DSM regarding hill slope landforms. Model performance was satisfactory, and good agreement with the conventional soil map demonstrates the importance of the DSM as a potential complementary tool for assisting soil mapping in mountainous areas in Brazil for the purpose of land use planning.

show abstract

Mapa digital de solos: uma proposta metodológica usando inferência fuzzy

Cited by 15 publications

References 7 publications

Soil Surveys in Brazil and Perspectives in Soil Digital Mapping

Soil Surveys in Brazil and Perspectives in Soil Digital Mapping

Comparison between detailed digital and conventional soil maps of an area with complex geology

Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area

Contact Info

Product

Resources

About