Ano de publicação: 2013

In this paper, we present a novel unsupervised algorithm, called CLimate and rEmote sensing Association patteRns Miner, for mining association patterns on heterogeneous time series from climate and remote sensing data integrated in a remote sensing information system developed to improve the monitoring of sugar cane fields. The system, called RemoteAgri, consists of a large database of climate data and low-resolution remote sensing images, an image preprocessing module, a time series extraction module, and time series mining methods. The preprocessing module was projected to perform accurate geometric correction, what is a requirement particularly for land and agriculture applications of satellite images. The time series extraction is accomplished through a graphical interface that allows easy interaction and high flexibility to users. The time series mining method transforms series to symbolic representation in order to identify patterns in a multitemporal satellite images and associate them with patterns in other series within a temporal sliding window. The validation process was achieved with agroclimatic data and NOAA-AVHRR images of sugar cane fields. Results show a correlation between agroclimatic time series and vegetation index images. Rules generated by our new algorithm show the association patterns in different periods of time in each time series, pointing to a time delay between the occurrences of patterns in the series analyzed, corroborating what specialists usually forecast without having the burden of dealing with many data charts

Time series analysis, Data mining, Remote sensing, Meteorology, Indexes, Satellites, Agriculture

http://ieeexplore.ieee.org/document/6215038/

Ano de publicação: 2011

O Brasil, o maior produtor mundial de cana-de-açúcar, é responsável por 35% da produção mundial. A produção de cana-de-açúcar se concentra nas regiões Centro-Sul e Nordeste e ocupa cerca de 8 milhões de hectares. A cana-de-açúcar, por apresentar um ciclo semi-perene, é influenciada pela variação das condições meteorológicas durante um ano inteiro. O objetivo do trabalho foi analisar os dados climáticos obtidos pelo modelo Eta (2011 a 2090) e os dados do clima atual (1991 a 2010) verificando suas implicações em relação a expansão da cana-de-açúcar no estado de São Paulo. Foram utilizados dados de precipitação e temperatura média, de 1991 a 2010, de estações meteorológicas de seis municípios de São Paulo. Para representar o cenário futuro (2011 a 2090), foram utilizados dados de precipitação e temperatura média obtidos pelo modelo Eta. A partir do balanço hídrico foi possível calcular a deficiência hídrica e o excedente hídrico para os municípios selecionados com armazenamento de água disponível no solo de 100mm. O balanço hídrico mostrou que haverá um aumento na deficiência hídrica. Com o aumento do período seco e do aumento da temperatura média poderá ocorrer uma queda na produtividade de sacarose da cana-de-açúcar.

water balance, Eta model, mean temperature

analise-comparativa-do-clima-atual-e-futuro-para-avaliar-a-expansao-da-cana-de-acucar-em-sao-paulo-02061715.pdf

http://www.cpa.unicamp.br/alcscens/docs/publicacoes/Analise%20comparativa%20do%20clima%20atual%20e%20futuro%20para%20avaliar%20a%20expansao%20da%20cana-de-acucar%20em%20Sao%20Paulo%20.pdf

Ano de publicação: 2011

Extremos de temperatura durante a fase do florescimento do café arábica causam abortamento de flores e perda na produção. Estudos de projeção climática, normalmente baseados em modelos de baixa resolução, já demonstram perdas na produção de café como conseqüência das altas temperaturas. No entanto, esses estudos têm uma menor precisão nas respostas por causa da resolução dos modelos, e novos estudos baseados em modelos de melhor resolução se tornam necessários. Este trabalho apresenta uma análise das implicações dos extremos de temperatura e precipitação na aptidão climática em municípios tradicionalmente produtores de café em Minas Gerais e São Paulo, utilizando o modelo climático Eta (40km de resolução). Primeiramente, as respostas do modelo foram comparadas com os dados climáticos atuais (dados observados). As projeções do modelo Eta foram satisfatórias porque seguem o padrão do clima já existente. Os dados do modelo demonstram um deslocamento do maior déficit hídrico do ano para o mês de setembro. O modelo projeta cenários com aumento de temperaturas, principalmente nos meses de setembro e outubro, que é o florescimento do café, impactando a produção de café arábica.

Aptidão climática, Café arábica, Eta

analise-dos-dados-de-projecao-climatica-do-modelo-eta-e-suas-implicacoes-para-a-cultura-do-cafe-arabica-02061715.pdf

Ano de publicação: 2011

O objetivo deste trabalho foi detectar municípios produtores de cana-de-açúcar no estado de São Paulo, similares, pelo método de agrupamento, analisando variáveis espectrais (NDVI), área plantada e produtividade no período de 2001 a 2009. O resultado dessa análise exploratória dos dados mostrou que a técnica é apropriada para a determinação de grupos de municípios com características semelhantes o que permite classificar as regiões automaticamente.

remote sensing, K-means biofuel

analise-temporal-de-municipios-produtores-cana-de-acucar-no-estado-de-sao-paulo-02061715.pdf

Ano de publicação: 2010

As condições meteorológicas são determinantes para a produção agrícola; a precipitação, em particular, pode ser citada como a mais influente por sua relação direta com o balanço hídrico. Neste sentido, modelos agrometeorológicos, os quais se baseiam nas respostas das culturas às condições meteorológicas, vêm sendo cada vez mais utilizados para a estimativa de rendimentos agrícolas. Devido às dificuldades de obtenção de dados para abastecer tais modelos, métodos de estimativa de precipitação utilizando imagens dos canais espectrais dos satélites meteorológicos têm sido empregados para esta finalidade. O presente trabalho tem por objetivo utilizar o classificador de padrões "floresta de caminhos ótimos" para correlacionar informações disponíveis no canal espectral infravermelho do satélite meteorológico GOES-12 com a refletividade obtida pelo radar do IPMET/UNESP localizado no município de Bauru, visando o desenvolvimento de um modelo para a detecção de ocorrência de precipitação. Nos experimentos foram comparados quatro algoritmos de classificação: redes neurais artificiais (ANN), k-vizinhos mais próximos (k-NN), máquinas de vetores de suporte (SVM) e floresta de caminhos ótimos (OPF). Este último obteve melhor resultado, tanto em eficiência quanto em precisão.

Classificadores Supervisionados, Floresta de Caminhos Ótimos, GOES, Estimativa de Ocorrência de Precipitação

http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0102-77862010000100002&lng=pt&tlng=pt

Ano de publicação: 2010

Weather conditions in critical periods of the vegetative crop development influence crop productivity, thus being a basic parameter for crop forecast. Reliable extended period weather forecasts may contribute to improve the estimation of agricultural productivity. The production of soybean plays an important role in the Brazilian economy, because this country is ranked among the largest producers of soybeans in the world. This culture can be significantly affected by water conditions, depending on the intensity of water deficit. This work explores the role of extended period weather forecasts for estimating soybean productivity in the southern part of Brazil, Passo Fundo, and Londrina (State of Rio Grande do Sul and Paraná, respectively) in the 2005/2006 harvest. The goal was to investigate the possible contribution of precipitation forecasts as a substitute for the use of climatological data on crop forecasts. The results suggest that the use of meteorological forecasts generate more reliable productivity estimates during the growth period than those generated only through climatological information.

Weather Forecast; Productivity Estimate; Ensemble Forecast; Forecast Period; Crop Cycle 

https://link.springer.com/article/10.1007%2Fs00704-010-0264-0

Ano de publicação: 2017

The intensification of drought incidence is one of the most important threats of the 21st century with significant effects on food security. Accordingly, there is a need to improve the understanding of the regional impacts of climate change on this hazard. This study assessed long-term trends in probability-based drought indices (Standardized Precipitation Index and Standardized Evapotranspiration Index) in the State of São Paulo, Brazil. Owing to the multi-scalar nature of both indices, the analyses were performed at 1 to 12-month time scales. The indices were calculated by means of a relativist approach that allowed us to compare drought conditions from different periods. The years 1961-1990 were used as the referential period. To the authors’ best knowledge, this is the first time that such relativist approach is used in historical trend analysis. The results suggest that the evapotranspiration rates have intensified the regional drought conditions. The time scale used to calculate the indices significantly affected the outcomes of drought trend assessments. The reason behind this feature is that the significant changes in the monthly regional patterns are limited to a specific period of the year. More specifically, virtually all significant changes have been observed during the first trimester of the rainy season (October, November and December). Considering that this period corresponds to critical plant growth stages (flowering/regrowth/sprouting) of several major crops (e.g. Sugarcane and Citrus), we may conclude that these significant changes have increased the risk of crop yield reductions due to agricultural drought.

intensification of drought; drought Index; agricultural drought; crop yields

http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0006-87052018000100201&lng=en&tlng=en

Ano de publicação: 2011

Agriculture appears to be one of the human activities most vulnerable to climatic changes due to its large dependence on environmental conditions. However, the diversity of Brazilian environmental conditions could be of great advantage to adapting this sector to new climatic conditions, which should be assessed as in this study on shifting Arabica coffee cultivation to the extreme south of the country. The methodology applied is the same the one used to define climatic risks in current productive regions of Brazil and their vulnerability to climatic change predicted by IPCC reports. The basic climatic parameters applied were frost probability and annual average temperature, since annual water deficit did not prove to be a restricting factor for Arabica coffee cultivation in the study area. The climatic conditions suitable for coffee production are: annual average temperature between 18°C and 22°C, annual water deficit less than 100 mm and frost probability (risk of lowest annual temperature less than 1°C) less than 25%. An area is said to have “low climatic risks” for coffee production when these three climatic conditions are met. Current climatic conditions were used and simulations of four temperature increases between 1°C and 4°C were also performed. The results indicated a substantial increase in the size of low climatic risks areas for the production of Arabica coffee in the extreme south of Brazil, mainly for mean temperature increases of 3°C in the study area in relation to present conditions. Increases of 2°C and 4°C were also favorable, but not as good as those obtained for 3°C. It should be underscored that areas with low climatic risks will be able to be found mainly in the extreme south of the study region, the border with Uruguay and North of Argentina.

Global Warming; Climatic Risk; Coffee Production; Current Climatic Condition; Arabica Coffee 

https://link.springer.com/article/10.1007%2Fs10584-011-0058-0

Ano de publicação: 2009

The decision correctness in expert systems strongly depends on the accuracy of a pattern classifier, whose learning is performed from labeled training samples. Some systems, however, have to manage, store, and process a large amount of data, making also the computational efficiency of the classifier an important requirement. Examples are expert systems based on image analysis for medical diagnosis and weather forecasting. The learning time of any pattern classifier increases with the training set size, and this might be necessary to improve accuracy. However, the problem is more critical for some popular methods, such as artificial neural networks and support vector machines (SVM), than for a recently proposed approach, the optimum-path forest (OPF) classifier. In this letter, we go beyond by presenting a robust approach to reduce the training set size and still preserve good accuracy in OPF classification. We validate the method using some data sets and for rainfall occurrence estimation based on satellite image analysis. The experiments use SVM and OPF without pruning of training patterns as baselines.

Robustness, Management training, Support vector machines, Support vector machine classification, Image analysis, Expert systems, Computational efficiency, Medical expert systems, Diagnostic expert systems, Medical diagnosis

http://ieeexplore.ieee.org/document/5357415/

Ano de publicação: 2017

Enhancing the capability of both standardized precipitation index (SPI) and standardized precipitation evapotranspiration index (SPEI) for quantifying wet and dry events under distinct climate conditions is of paramount importance. The different recommendations of recent studies regarding the best distribution to calculate the SPEI and the lack of studies addressing the effect of different parameters estimation methods on the SPI motivated us to apply and adapt distinct testing methodologies to select candidate models for calculating these standardized drought indices (SDI). The study is based on two data sets. The first represents a tropical–subtropical region of Brazil. The second comprises the same weather stations that were used for developing the original version of the SPEI. The study also emphasized the performance of the models within the range of typical SDI values [−2.0 : 2.0]. Along with goodness‐of‐fit tests, we calculated the mean absolute errors between the indices values estimated from the candidate distributions, and their corresponding theoretical values derived from the standard normal distribution. The two‐parameter gamma and the generalized extreme value distributions are, respectively, recommended for general use in SPI and SPEI algorithms (1–12‐month timescales). The unbiased probability weighted moments are recommended to estimate the distributions parameters. The study also described a trade‐off between choosing the best model for the central part and for the tails of the distributions. This trade‐off suggests that the methodologies used to select models for the SDI algorithms may have to decide which part of the distribution (central or tails) should be emphasized. The behaviour of the errors among different wet/dry categories showed that both indices were only capable of representing drought and floods in a similar probabilistic way within the range [−2.0 : 2.0]. This feature supports our decision to emphasize model performances within such range.

drought; standardized precipitation index; standardized precipitation evapotranspiration index; trade-off; param-eter estimation

https://rmets.onlinelibrary.wiley.com/doi/full/10.1002/joc.5381