Exploring Current Trends in Agricultural Commodities Forecasting Methods through Text Mining: Developments in Statistical and Artificial Intelligence Methods DOI Creative Commons

Luana Gonçalves Guindani,

Gilson Adamczuk Oliveirai,

Matheus Henrique Dal Molin Ribeiro

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(23), P. e40568 - e40568

Published: Nov. 20, 2024

Agriculture stands as one of the major economic pillars worldwide, with food production contributing significantly to income growth. However, agricultural activities also entail risks associated uncontrollable factors along supply chain. To address these challenges, mathematical models have been developed for forecasting crucial variables in managing agribusiness activities. In this context, article employs a combination systematic bibliometric analysis and Latent Dirichlet Allocation (LDA) method, semi-automated approach. The main objective study was automate identification relevant topics construct bibliographic portfolio (BP) covering period 2015-2022, focusing on methodologies used articles other analyses. 30 included BP issues related applied temporal commodities. These were categorized based nature prediction used, classified (i) machine learning (ML), (ii) artificial neural networks (ML-NN), (iii) ensemble (ML-Ensemble), (iv) hybrid (ML-hybrid), (v) statistical. Regarding results, topic that stood out most termed "Forecasting Methods Applied Agribusiness Time Series." utilized classes ML-hybrid (41.95 %) statistical (29.31 %), followed by ML-NN (14.94 ML (9.20 ML-Ensemble (4.60 types. theoretical contribution lies identifying literary gaps concerning methods agribusiness, while its practical implication is identify support decision-making.

Language: Английский

Enhanced industrial heat load forecasting in district networks via a multi-scale fusion ensemble deep learning DOI
Zhiqiang Chen, Yang Yu, Chundi Jiang

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 272, P. 126783 - 126783

Published: Feb. 8, 2025

Language: Английский

Citations

1
Real-time Error Compensation Transfer Learning with Echo State Networks for Enhanced Wind Power Prediction DOI Creative Commons
Yingqin Zhu, Yue Liu, Nan Wang

et al.

Applied Energy, Journal Year: 2024, Volume and Issue: 379, P. 124893 - 124893

Published: Nov. 26, 2024

Language: Английский

Citations

5
Hypertuned wavelet convolutional neural network with long short-term memory for time series forecasting in hydroelectric power plants DOI
Stéfano Frizzo Stefenon, Laio Oriel Seman, Evandro Cardozo da Silva

et al.

Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133918 - 133918

Published: Nov. 1, 2024

Language: Английский

Citations

4
Assessment of hybrid kernel function in extreme support vector regression model for streamflow time series forecasting based on a bayesian estimator decomposition algorithm DOI
Peng Shi, Lei Xu, Simin Qu

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 149, P. 110514 - 110514

Published: March 15, 2025

Language: Английский

Citations

0
Signal processing techniques for detecting leakage in urban water supply pipelines: Denoising and feature enhancement DOI

Liang Ma,

Tao An, Runhan Zhao

et al.

Tunnelling and Underground Space Technology, Journal Year: 2025, Volume and Issue: 162, P. 106670 - 106670

Published: April 24, 2025

Language: Английский

Citations

0
Time Series Forecasting of Natural Inflow in Hydroelectric Power Plants Using Hyper‐Tuned Temporal Fusion Transformer With Hodrick–Prescott Filter DOI Creative Commons
Rafael Ninno Muniz, William Gouvêa Buratto, Ademir Nied

et al.

IET Generation Transmission & Distribution, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

ABSTRACT The scheduling of the operation electricity system in Brazil is based on multi‐criteria optimization that takes into account forecast level dams hydroelectric plants, this variation evaluated by soil moisture active passive model. Considering advances using deep learning to time series variations, paper proposes a hybrid method for forecasting dam variations. In particular, temporal fusion transformer (TFT) used prediction with Hodrick–Prescott filter denoising. To enhance model's performance, its hyperparameters are optimized Optuna framework tree‐structured Parzen estimator. For benchmarking, multilayer perceptron, long short‐term memory, recurrent neural network (RNN), Dilated RNN, convolutional neural, hierarchical interpolation forecasting, non‐parametric forecaster, and standard TFT considered. results show proposed model can make predictions high performance compared other methods, being 29.12% better than second‐best model, 59.22% original very making it promising alternative be as additional information planning electrical power system.

Language: Английский

Citations

0
Wind speed forecasting approach using conformal prediction and feature importance selection DOI

Cesar Vinicius Zuege,

Stéfano Frizzo Stefenon, Cristina Keiko Yamaguchi

et al.

International Journal of Electrical Power & Energy Systems, Journal Year: 2025, Volume and Issue: 168, P. 110700 - 110700

Published: May 12, 2025

Language: Английский

Citations

0
Prediction of non-stationary daily streamflow series based on ensemble learning: a case study of the Wei River Basin, China DOI
Wei Ma, Xiao Zhang, Jiancang Xie

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 18, 2024

Language: Английский

Citations

1
Exploring Current Trends in Agricultural Commodities Forecasting Methods through Text Mining: Developments in Statistical and Artificial Intelligence Methods DOI Creative Commons

Luana Gonçalves Guindani,

Gilson Adamczuk Oliveirai,

Matheus Henrique Dal Molin Ribeiro

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(23), P. e40568 - e40568

Published: Nov. 20, 2024

Agriculture stands as one of the major economic pillars worldwide, with food production contributing significantly to income growth. However, agricultural activities also entail risks associated uncontrollable factors along supply chain. To address these challenges, mathematical models have been developed for forecasting crucial variables in managing agribusiness activities. In this context, article employs a combination systematic bibliometric analysis and Latent Dirichlet Allocation (LDA) method, semi-automated approach. The main objective study was automate identification relevant topics construct bibliographic portfolio (BP) covering period 2015-2022, focusing on methodologies used articles other analyses. 30 included BP issues related applied temporal commodities. These were categorized based nature prediction used, classified (i) machine learning (ML), (ii) artificial neural networks (ML-NN), (iii) ensemble (ML-Ensemble), (iv) hybrid (ML-hybrid), (v) statistical. Regarding results, topic that stood out most termed "Forecasting Methods Applied Agribusiness Time Series." utilized classes ML-hybrid (41.95 %) statistical (29.31 %), followed by ML-NN (14.94 ML (9.20 ML-Ensemble (4.60 types. theoretical contribution lies identifying literary gaps concerning methods agribusiness, while its practical implication is identify support decision-making.

Language: Английский

Citations

0