Ensemble data mining approaches to forecast regional sugarcane crop production

Everingham, Yvette; Smyth, Christine; Inman-Bamber, N. G.

doi:10.1016/j.agrformet.2008.10.018

Cited by 44 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ainda mais, os resultados das simulações proporcionam conhecimentos que possibilitam recomendar práticas para redução dos riscos ambientais e dos custos de produção, resultando em maior sustentabilidade do planejamento agrícola (Gouvêa et al, 2009). Everingham et al (2009) enfatizam que as previsões de produção são úteis para o sucesso de qualquer indústria agrícola que planeja ou vende a produção antes da colheita.…”

Section: Introductionunclassified

Estimativa da produtividade da cana-de-açúcar para as principais regiões produtoras de Minas Gerais usando-se o método ZAE I

Oliveira¹,

Santos²,

Ribeiro³

et al. 2012

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

RESUMO Objetivou-se, com este trabalho, parametrizar, calibrar e testar o método da Zona Agroecológica (ZAE) para as principais regiões produtoras de cana-de-açúcar do Estado de Minas Gerais. Foram utilizados dados meteorológicos do Instituto Nacional de Meteorologia e da Agência Nacional de Águas e dados de produtividade do Programa de Melhoramento Genético da Cana-de-Açúcar. O método ZAE apresentou bom ajuste, com R2 = 0,89; RMSE = 8,4 t ha-1; MAE = 6,7 t ha-1; MBE = 5,9 t ha-1 e índice de Wilmont (d) = 0,95. Na validação realizada mediante a utilização de uma série temporal de dados de produtividade do Instituto Brasileiro de Geografia e Estatística das safras de 1989/90 a 2007/08, referente à região do Triângulo Mineiro, constatou-se um erro sistemático com tendência de superestimativa da produtividade de aproximadamente 37 t ha-1. Corrigindo-se a tendência de superestimativa o método ZAE apresentou ajuste satisfatório (R2 = 0,55; RMSE = 4,9 t ha-1; MAE = 4,0 t ha-1; MBE = 0,0 t ha-1; índice d = 0,80). Assim, este modelo se apresentou como importante ferramenta para estimar a produtividade da cana-de-açúcar em macroescala no Estado, podendo auxiliar no planejamento da expansão otimizada da atividade na região.

show abstract

Section: Introductionunclassified

Estimativa da produtividade da cana-de-açúcar para as principais regiões produtoras de Minas Gerais usando-se o método ZAE I

Oliveira¹,

Santos²,

Ribeiro³

et al. 2012

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

show abstract

“…Random forest regression models were built using 500 trees The Agricultural Production Systems Simulator (Keating et al 1999) was used to simulate sugarcane accumulated biomass throughout the growing season. The APSIM biomass index (AI) was generated using an ensemble modelling approach (Everingham et al 2015a;Everingham et al 2009). The Ensemble approach considered a range of APSIM parameterizations represented in the Tully region.…”

Section: Random Forestsmentioning

confidence: 99%

“…Ensemble methods involve making multiple attempts from different data or models to predict a response variable like sugarcane yields. Using multiple efforts to predict a response can increase the robustness and accuracy of predictions compared to using any single data set or model (Breiman 2001;Everingham et al 2009). We stress that random forest models should not be confused with the single decision tree approach like that adopted in classification and regression trees (De'ath and Fabricius 2000).…”

Section: Introductionmentioning

confidence: 99%

Accurate prediction of sugarcane yield using a random forest algorithm

Everingham

Sexton

Skocaj

et al. 2016

Agron. Sustain. Dev.

262

View full text Add to dashboard Cite

Foreknowledge about sugarcane crop size can help industry members make more informed decisions. There exists many different combinations of climate variables, seasonal climate prediction indices, and crop model outputs that could prove useful in explaining sugarcane crop size. A data mining method like random forests can cope with generating a prediction model when the search space of predictor variables is large. Research that has investigated the accuracy of random forests to explain annual variation in sugarcane productivity and the suitability of predictor variables generated from crop models coupled with observed climate and seasonal climate prediction indices is limited. Simulated biomass from the APSIM (Agricultural Production Systems sIMulator) sugarcane crop model, seasonal climate prediction indices and observed rainfall, maximum and minimum temperature, and radiation were supplied as inputs to a random forest classifier and a random forest regression model to explain annual variation in regional sugarcane yields at Tully, in northeastern Australia. Prediction models were generated on 1 September in the year before harvest, and then on 1 January and 1 March in the year of harvest, which typically runs from June to November. Our results indicated that in 86.36 % of years, it was possible to determine as early as September in the year before harvest if production would be above the median. This accuracy improved to 95.45 % by January in the year of harvest. The R-squared of the random forest regression model gradually improved from 66.76 to 79.21 % from September in the year before harvest through to March in the same year of harvest. All three sets of variables-(i) simulated biomass indices, (ii) observed climate, and (iii) seasonal climate prediction indices-were typically featured in the models at various stages. Better crop predictions allows farmers to improve their nitrogen management to meet the demands of the new crop, mill managers could better plan the mill's labor requirements and maintenance scheduling activities, and marketers can more confidently manage the forward sale and storage of the crop. Hence, accurate yield forecasts can improve industry sustainability by delivering better environmental and economic outcomes.

show abstract

“…A novel neural network ensemble approach called the generalized regression neural network ensemble for time series forecasting (GEFTSGRNN) which is a concatenation of existing machine learning algorithms has been applied in benchmark time series forecasting datasets by Gheyas and Smith (2011). Everingham et al (2009) constructed an ensemble method comprising statistical data mining models, to forecast crop productions in north eastern Australia.…”

Section: Introductionmentioning

confidence: 99%

A rainfall forecasting method using machine learning models and its application to the Fukuoka city case

Sumi¹,

Zaman²,

Hirose³

2012

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

In the present article, an attempt is made to derive optimal data-driven machine learning methods for forecasting an average daily and monthly rainfall of the Fukuoka city in Japan. This comparative study is conducted concentrating on three aspects: modelling inputs, modelling methods and pre-processing techniques. A comparison between linear correlation analysis and average mutual information is made to find an optimal input technique. For the modelling of the rainfall, a novel hybrid multi-model method is proposed and compared with its constituent models. The models include the artificial neural network, multivariate adaptive regression splines, the k-nearest neighbour, and radial basis support vector regression. Each of these methods is applied to model the daily and monthly rainfall, coupled with a pre-processing technique including moving average and principal component analysis. In the first stage of the hybrid method, sub-models from each of the above methods are constructed with different parameter settings. In the second stage, the sub-models are ranked with a variable selection technique and the higher ranked models are selected based on the leave-one-out cross-validation error. The forecasting of the hybrid model is performed by the weighted combination of the finally selected models.

show abstract

Ensemble data mining approaches to forecast regional sugarcane crop production

Cited by 44 publications

References 22 publications

Estimativa da produtividade da cana-de-açúcar para as principais regiões produtoras de Minas Gerais usando-se o método ZAE I

Estimativa da produtividade da cana-de-açúcar para as principais regiões produtoras de Minas Gerais usando-se o método ZAE I

Accurate prediction of sugarcane yield using a random forest algorithm

A rainfall forecasting method using machine learning models and its application to the Fukuoka city case

Contact Info

Product

Resources

About