Climate and environmental data contribute to the prediction of grain commodity prices using deep learning

Wang，Zilin1; French，Niamh2; James，Thomas2; Schillaci，Calogero3; Chan，Faith4,5,6; Feng，Meili4; Lipani，Aldo1

2023-09-01

10.1002/sae2.12041

Journal of Sustainable Agriculture and Environment   Impact Factor & Quartile

2767-035X

Background: Grain commodities are important to people's daily lives and their fluctuations can cause instability for households. Accurate prediction of grain prices can improve food and social security. Methods & Materials: This study proposes a hybrid Long Short-Term Memory (LSTM)-Convolutional Neural Network (CNN) model to forecast weekly oat, corn, soybean and wheat prices in the United States market. The LSTM-CNN is a multivariate model that uses weather data, macroeconomic data, commodities grain prices and snow factors, including Snow Water Equivalent (SWE), snowfall and snow depth, to make multistep ahead forecasts. Results: Of all the features, the snow factor is used for the first time for commodity price forecasting. We used the LSTM-CNN model to evaluate the 5, 10, 15 and 20 weeks ahead forecasting and this hybrid model had the lowest Mean Squared Error (MSE) at 5, 10 and 15 weeks ahead of prediction. In addition, Shapley values were calculated to analyse the feature contribution of the LSTM-CNN model when forecasting the testing set. Based on the feature contribution, SWE ranked third, fifth and seventh in feature importance in the 5-week ahead forecast for corn, oats and wheat, respectively, and 7–8 places higher than total precipitation, indicating the potential use of SWE in grain price forecasting. Conclusion: The hybrid multivariate LSTM-CNN model outperformed other models and the newly involved climate data, SWE, showed the research potential of using snow as an input variable to predict grain prices over a multistep ahead time horizon.

commodity prices LSTM-CNN multistep ahead prediction snow water equivalent

English

Others

2-s2.0-85170038962

Scopus

1.University College London (UCL),London,United Kingdom
2.Wegaw SA,Trélex,Switzerland
3.European Commission,Joint Research Centre (JRC),Ispra,VA,Italy
4.School of Geographical Sciences,University of Nottingham Ningbo China,Ningbo,China
5.Water@Leeds and School of Geography,University of Leeds,Leeds,United Kingdom
6.Research Centre for Intelligent Management & Innovation Development/Research Base for Shenzhen Municipal Policy & Development,Southern University of Science and Technology,Shenzhen,China

Wang，Zilin,French，Niamh,James，Thomas,et al. Climate and environmental data contribute to the prediction of grain commodity prices using deep learning[J]. Journal of Sustainable Agriculture and Environment,2023,2(3):251-265.

Wang，Zilin.,French，Niamh.,James，Thomas.,Schillaci，Calogero.,Chan，Faith.,...&Lipani，Aldo.(2023).Climate and environmental data contribute to the prediction of grain commodity prices using deep learning.Journal of Sustainable Agriculture and Environment,2(3),251-265.

Wang，Zilin,et al."Climate and environmental data contribute to the prediction of grain commodity prices using deep learning".Journal of Sustainable Agriculture and Environment 2.3(2023):251-265.