Integration of principal component analysis and artificial neural networks to more effectively predict agricultural energy flows

Abstract

There are some studies regarding the prediction of agricultural energy flows using artificial neural networks (ANNs). These models are quite sensitive to correlations amongst inputs, and, there are often strong correlations amongst energy inputs for agricultural systems. One potential method to remediate this problem is to use principal component analysis (PCA). Therefore, the purpose of this research was to predict energy flows for a specific agricultural system (Iranian tea production) via a novel methodology based on ANNs, and using principal components as model inputs, not raw data. PCA results showed that the first and second components could account for more than 99% of variation in the data, thus the dimensions of the data set could be decreased from six to two for the prediction of energy flows for Iranian tea production. Using these principal components as inputs, an ANN model with 2–15–1 structure was determined to be optimal for energy flow modeling of this system. To conclude, the results of this study highlighted that the use of PC as ANN inputs improved ANN model prediction through reducing its complexity and eliminating data colinearity. Many agricultural systems could benefit from using this methodology for energy modeling. © 2019 American Institute of Chemical Engineers Environ Prog, 38:e13130, 2019

Principal component analysis of day‐ahead electricity price forecasting in CAISO and its implications for highly integrated renewable energy markets

“…In contrast, machine learning techniques rely on algorithms and data‐driven approaches like PCA, ANN, SVM, decision trees, and random forests to make predictions based on historical data (Bose, 2017; Nikkhah et al, 2019). Econometric models focus on economic factors impacting electricity prices like multi‐agent or game theoretic simulations, to analyze relationships between variables that influence electricity prices, such as weather, fuel prices, and demand (Ali & Choi, 2020; Nyangon & Byrne, 2023).…”

Competitiveness and sustainable development of Chinableapple industry

“…Through the analysis of agricultural economic competitiveness at different levels, the specific problems of each main production area of the apple industry in China were clarified, and reasonable countermeasures and suggestions were developed. Second, we used principal component analysis [ 37 , 38 ] and space exploration analysis [ 39 ] as the research methods. Third, we analyzed the changes in the competitiveness of the eight main apple-producing areas and selected the two-year apple-related data in 2004 and 2018 to explore the development and prospects of China’s apple industry competitiveness; we analyzed the spatial differentiation characteristics of China’s apple industry competitiveness, evaluated the sustainable development potential of the apple industry, which contributes to the development of the apple industry, and provided relevant advice on agricultural progress, with a view to promoting the sustainable development of the apple industry.…”

Prediction of Agro Products Sales Using Regression Algorithm

“…Principal Component Analysis: Research had surfaced on prediction of agricultural energy and Nikkhah et al [17] identified that a problem of strong correlation from among the energy inputs in agricultural systems existed when the Artificial Neural Networks model was used and so they used the principal components as model input and not as raw data and the result showed that an improved ANN model prediction.…”