Eliseu Jose Weber

Decision trees for digital soil mapping on subtropical basaltic steeplands

When soil surveys are not available for land use planning activities, digital soil mapping techniques can be of assistance. Soil surveyors can process spatial information faster, to assist in the execution of traditional soil survey or predict the occurrence of soil classes across landscapes. Decision tree techniques were evaluated as tools for predicting the ocurrence of soil classes in basaltic steeplands in South Brazil. Several combinations of types of decicion tree algorithms and number of elements on terminal nodes of trees were compared using soil maps with both original and simplified legends. In general, decision tree analysis was useful for predicting occurrence of soil mapping units. Decision trees with fewer elements on terminal nodes yield higher accuracies, and legend simplification (aggregation) reduced the precision of predictions. Algorithm J48 had better performance than BF Tree, RepTree, Random Tree, and Simple Chart.

Traffic Crashes and Alcohol Outlets in a Brazilian State Capital

Objective: Restricting alcohol outlets is being considered as a measure for preventing alcohol-related crashes. However, in many developing countries, alcohol availability is not regulated and its influence on motor vehicle traffic crashes is unknown. This study explores the association between traffic crashes and alcohol outlets in a Brazilian city. Method: Data were geocoded and exploratory analysis was conducted using the kernel density estimator. Two generalized additive models (GAMs) were implemented to predict the factors associated with alcohol-related crashes. Results: For 78 percent of the 3840 traffic crashes where the driver was a victim, there was at least one bar located within a 300-m radius. The median distances between an outlet were 124.4 and 130.7 m for a non-alcohol- and alcohol-related crashes, respectively (P =.13). The GAMs did not make evident any significant association between the outlet locations and alcohol-related crashes: the presence of at least one outlet was associated with alcohol-related crashes with an odds ratio (OR) of 0.94 (95% confidence interval [CI] = 0.75–1.17). Alcohol crashes are more likely to be observed among males (OR = 1.58; 95% CI = 1.21–2.06), young drivers vs. those aged 50 years+ (OR = 3.4; 95% CI = 1.79–6.43), and crashes with fatalities (OR = 1.73; 95% CI = 0.98–3.04). Conclusions: Density of alcohol outlets was high all over the city and both alcohol- and non-alcohol-related crashes occurred near an outlet. The study helps to better understand the relationship between alcohol availability and traffic crashes in a middle-income country where licensing/zoning is absent and suggests that measures for restricting the physical availability of alcohol are necessary, even though further studies are still needed.

Prediction of soil orders with high spatial resolution: response of different classifiers to sampling density

O objetivo deste trabalho foi avaliar a densidade de amostragem na acuracia de predicao de ordens de solos, com alta resolucao espacial, em area viticola da Serra Gaucha. Para isso, utilizou-se modelo digital de elevacao (MDE) do terreno, base cartografica, mapa convencional de solos e o programa Idrisi. Sete variaveis preditoras foram calculadas e lidas junto com as classes de solo, em pontos aleatoriamente distribuidos, nas densidades de 0,5, 1, 1,5, 2 e 4 pontos por hectare. Os dados foram usados para treinar uma arvore de decisao (Gini) e tres redes neurais artificiais: teoria da ressonância adaptativa, fuzzy ARTMap; mapa auto‑organizavel, SOM; e perceptron de multiplas camadas, MLP. Os mapas estimados foram comparados com o mapa de solos convencional para calcular erros de omissao e de inclusao, exatidao geral, e erros de quantidade e de alocacao. A arvore de decisao foi menos sensivel a densidade de amostragem e apresentou maior acuracia e consistencia. O SOM foi a rede neural com menor sensibilidade e maior consistencia. O MLP apresentou minimo critico e maior inconsistencia, enquanto fuzzy ARTMap apresentou maior sensibilidade e menor acuracia. Os resultados indicam que densidades de amostragem usadas em levantamentos convencionais podem servir de referencia para estimar ordens de solos na Serra Gaucha.

Sistema de informação geográfica como apoio ao levantamento detalhado de solos do Vale dos Vinhedos

This study proposes the use of geotechnologies to support detailed soil surveys, from field surveys to the delimitation of mapping units and later the drawing of the final map. The study area corresponds to a topographic map on a scale of 1:5,000 of the Vale dos Vinhedos, in the Serra Gaucha region, State of Rio Grande do Sul, Brazil. The material used consists of planialtimetric data derived from aerial photographs, navigation GPS (Global Positioning System), and GIS (Geographical Information System) software. The GIS program was used to integrate field data with cartographic information and with a DTM (Digital Terrain Model). Results show that the methodology can generate a georreferenced digital map in which soil mapping units are strongly associated with relief phases, improving the consistency and reliability as well as making the use in further applications easier.

GIS as a Support to Soil Mapping in Southern Brazil

Traditional soil surveys follow a specific methodology to identify, characterize, and fit mapping units in a classification system and to spatialize them in order to produce soil maps. The need for observation and characterization on field, associated with the physical and chemical analyses, makes the surveys expensive and therefore scarce. The low number of surveys stimulated the development of models for digital soil mapping, whose results proved to be possible to predict and spatialize many soil characteristics. However, conventional soil surveys remain important as a basis for the development of digital soil mapping models, setting a reason to continue the development of methodologies to improve the conventional surveys. Technologies like GPS and GIS contribute to make field observation and soil sampling more objective and make the mapping process and the production of hardmaps easier and faster. The objective of this study was to develop methodologies to integrate cartographic base elements with field work, using GIS and GPS in an area corresponding to 20 topographic charts in scale 1:50,000 in the State of Rio Grande do Sul, Southern Brazil, to obtain soil mapping based on the Brazilian Soil Classification System. The result obtained was a georeferenced digitized soil map, continuous for the whole region, free of inconsistency among neighbor map sheets and with attributes associated with the mapping units. These characteristics allow the use and application of the soil map for many purposes like zoning, diagnosis, suitability analysis as well as serving as a basis to the development of models for digital soil mapping.

Indicadores geoespaciais para avaliação do impacto ambiental da suinocultura no licenciamento em âmbito municipal

The objective of this work was to propose and evaluate geospatial indicators to analyze the environmental impact of swine production on licensing at municipal level. The study was conducted in the municipality of Quinze de Novembro, in the state of Rio Grande do Sul, Brazil. Environmental indicators in farmlands and watersheds were evaluated. A geospatial database was created using Geographic Information Systems and a systematic survey of swine farmers and farmlands receiving pig slurry, which included swine farms, current land use, soil types, drainage net, and digital elevation model. The geospatial indicators obtained with the geoprocessing tools were: watershed areas with application of swine slurry; areas of permanent preservation and for recovery; application rate of swine slurry; slope; resistance to degradation; distance between farmlands with swine slurry application and watercourse; width of potential buffer zone between farmlands and watercourse; distance between swine barns and watercourse; conflict between facilities and preservation areas; and areas that need environmental recovery. The interpretation of these indicators enables evaluating the potential environmental impacts of swine production in farmlands and watersheds where they are located, which allows to identify the locations with greater risks and to aid the environmental licensing of this activity.

Caracterização de mapas legados de solos: uso de indicadores em mapas com diferetens escalas no Rio Grande do Sul

Mapas convencionais de solos tem adquirido importância crescente como entrada para diversas aplicacoes, muitas vezes sem levar em conta a sua qualidade deles. O objetivo deste estudo foi descrever e comparar mapas de solos usando indicadores quantitativos de facil determinacao. Foram utilizados nove mapas elaborados em diferentes escalas no Rio Grande do Sul e o software ArcGIS. Calcularam-se a escala efetiva, o numero de poligonos menores que a area minima mapeavel e um indice de complexidade de forma, e quantificaram-se o numero de classes taxonomicas, de tipos de solos e de unidades de mapeamento e a fracao da area com dados nao uniformes. Os resultados evidenciaram que a qualidade de mapas de solos tende a ser inferior ao presumido para sua escala de apresentacao, o que demonstra a importância e a necessidade de avaliacoes previas ao seu uso. Indicadores computados a partir dos poligonos e da legenda possibilitam avaliacao rapida e objetiva, com potencial de aplicacao na sistematizacao e documentacao de dados legados de solos no Brasil.

Obstrução do horizonte calculada a partir de modelo digital de elevação

O objetivo deste trabalho foi avaliar a exatidao do calculo da obstrucao do horizonte, a partir de um modelo digital de elevacao (MDE), em diferentes situacoes topograficas. O material utilizado incluiu um MDE disponivel para a regiao da Serra Gaucha, RS, receptores GPS, câmera digital, lente grande‑angular e os programas Idrisi, Arcview/ArcGIS e Solar Analyst. Foram adquiridas fotografias hemisfericas, e coletadas as coordenadas de 16 locais na area de estudo. As coordenadas e o MDE foram utilizados para calcular a obstrucao do horizonte com uso do algoritmo Solar Analyst. Foram comparadas a fracao aberta do ceu calculada e a obtida pelas fotografias hemisfericas. O coeficiente de determinacao foi de 0,8428, tendo-se observado superestimativa media de 5,53% da fracao aberta do ceu. Os erros sao atribuidos principalmente a obstrucao pela vegetacao, que nao pode ser identificada pelo MDE. A obstrucao do horizonte, causada pelo relevo na Serra Gaucha, pode ser calculada satisfatoriamente pelo Solar Analyst, a partir de um MDE interpolado de cartas topograficas na escala 1:50.000.

Identification of foot and mouth disease risk areas using a multi-criteria analysis approach

Foot and mouth disease (FMD) is a highly infectious disease that affects cloven-hoofed livestock and wildlife. FMD has been a problem for decades, which has led to various measures to control, eradicate and prevent FMD by National Veterinary Services worldwide. Currently, the identification of areas that are at risk of FMD virus incursion and spread is a priority for FMD target surveillance after FMD is eradicated from a given country or region. In our study, a knowledge-driven spatial model was built to identify risk areas for FMD occurrence and to evaluate FMD surveillance performance in Rio Grande do Sul state, Brazil. For this purpose, multi-criteria decision analysis was used as a tool to seek multiple and conflicting criteria to determine a preferred course of action. Thirteen South American experts analyzed 18 variables associated with FMD introduction and dissemination pathways in Rio Grande do Sul. As a result, FMD higher risk areas were identified at international borders and in the central region of the state. The final model was expressed as a raster surface. The predictive ability of the model assessed by comparing, for each cell of the raster surface, the computed model risk scores with a binary variable representing the presence or absence of an FMD outbreak in that cell during the period 1985 to 2015. Current FMD surveillance performance was assessed, and recommendations were made to improve surveillance activities in critical areas.

Avaliação multicritério aplicada ao mapeamento a suscetibilidade a escorregamentos: o caso do Bairro Cascata, Porto Alegre, RS (Multicriteria analysis applied to landslide susceptibility mapping: a case study in Cascata District, Porto Alegre, RS )

O objetivo deste estudo foi mapear, com o emprego de uma tecnica de avaliacao multicriterio em ambiente SIG, a suscetibilidade a escorregamentos no bairro Cascata, Porto Alegre. As variaveis utilizadas foram: declividade, litologia, pedologia, uso do solo e cobertura vegetal. Apos a padronizacao das variaveis, definiu-se a importância de cada uma na predisposicao do terreno a escorregamentos com o apoio da tecnica de avaliacao multicriterio AHP (Analytic Hierarchy Process). Os resultados indicam que 3,27% da area de estudo possui alta suscetibilidade; 83,29% media; 11,98% baixa e 1,46% muito baixa. Verificou-se tambem que 70,12% da classe alta suscetibilidade ja foi urbanizada, configurando-se em areas prioritarias para a mitigacao de riscos. Esse quadro tende a se agravar, uma vez que a expansao urbana e inevitavel e continua, e que a medida que a populacao cresce, ela modifica o territorio, potencializando a ocorrencia desses desastres. Dessa forma, o mapa resultante constitui-se em subsidio importante para a tomada de decisao, possibilitando uma escolha mais racional na definicao de estrategias de prevencao e intervencao do poder publico. Isso demonstra que o geoprocessamento aliado a tecnicas de avaliacao multicriterio, simplifica e torna agil o mapeamento da suscetibilidade. This study aims to map, with the use of a multi-criteria analysis (MCA) technique in a GIS environment, the landslide susceptibility in the Cascata district, Porto Alegre, Brazil. Variables used were: slope, geology, soil, land use and vegetation cover. After the standardization of these variables, their importance for landslides predisposition was defined with the support of the multi-criteria technique AHP (Analytic Hierarchy Process). Results indicate that 3.27% of the study area has a high susceptibility; 83.29% moderate, 11.89% low and 1.46% very low. It was also found that 70.12% of the high susceptibility class has already been urbanized, and therefore, should be considered as priority for risk mitigation. This situation tends to worsen since urban sprawl is inevitable and continuous, and as the populations grow, it changes the territory, enhancing the occurrence of these disasters. Thus, the resulting map is an important tool for decision making, enabling a more rational definition of public strategies for landslides prevention and intervention. This demonstrates that GIS combined with MCA techniques simplifies and makes the susceptibility mapping faster. Keywords: landslides, GIS, susceptibility, MCA, AHP.