Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Applied Agricultural Science and Technology Agricultural Revolution Journal
Dita Fitriani
Universitas Lancang Kuning
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Materials Science & Nanotechnology

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Performance Evaluation of ARIMA and ANN Models for Forecasting Oil Palm Production Trends Hermiza Mardesci; Dita Fitriani
Agricultural Revolution Journal Vol. 1 No. 2 (2025): Agricultural Revolution Journal
Publisher : CIB Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64570/agrivolution.v1i2.33

Abstract

This study compares the performance of the Autoregressive Integrated Moving Average (ARIMA) model and an Artificial Neural Network (ANN) in forecasting annual palm oil production in Kampar Regency, using a univariate time series covering the period from 2013 to 2024. The forecasting aim is to support regional agricultural planning and decision-making in one of Riau Province’s key oil palm-producing regions. The ARIMA model was developed using the Box–Jenkins approach, which involves stationarity testing, optimal model identification, parameter estimation, and residual diagnostics, including ACF/PACF, Shapiro–Wilk, Jarque–Bera, and Ljung–Box tests. A feedforward ANN with three lagged inputs, five hidden neurons, sigmoid activation, and backpropagation training was constructed for comparison. Model performance was evaluated using RMSE, MAPE, and R². The results indicate that the ARIMA (1,1,1) model yields more stable and reliable forecasts, with diagnostic tests confirming white noise residuals and no significant autocorrelation. Conversely, the ANN model produced higher errors and indications of overfitting, likely due to the limited number of observations and the sharp increase in production recorded in the final data year. While ANN captured a stronger upward trend, which may represent an optimistic scenario, ARIMA provided more conservative and statistically valid forecasts under constrained data conditions. Overall, the ARIMA(1,1,1) model proved more suitable for the short univariate palm oil production series, yielding lower forecasting errors (RMSE = 273.88; MAPE = 8.92%) than the ANN model (RMSE = 283.53; MAPE = 9.03%).
Integrating Climate Variables into Coconut Production Forecasting: A Comparative Analysis of ARIMA and ARIMAX Models for Climate-Informed Decision Support Hermiza Mardesci; Mulono Apriyanto; Dita Fitriani; Herman Farmi; Abdullah Abdullah
Journal of Applied Agricultural Science and Technology Vol. 10 No. 3 (2026): Journal of Applied Agricultural Science and Technology
Publisher : Green Engineering Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55043/jaast.v10i3.558

Abstract

Coconut is a strategic plantation commodity in Padang Pariaman Regency, Indonesia, whose productivity is increasingly influenced by climate variability. Accurate, climate-responsive forecasting is therefore essential to support production planning and early warning systems. This study aims to develop and evaluate a climate-informed ARIMAX model for forecasting coconut production and assessing its potential application in an early warning framework. Annual coconut production data for 2014–2024 were combined with climate variables, including rainfall, temperature, humidity, wind speed, and the number of rainy days. A baseline ARIMA model was first identified, followed by ARIMAX modeling using Maximum Likelihood Estimation. Model selection was based on Akaike Information Criterion (AIC), while forecasting performance was evaluated using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results showed that ARIMA(1,1,1) was identified as the optimal baseline model and achieved the lowest forecasting errors based on RMSE and MAPE, indicating its strong capability in capturing the temporal pattern of coconut production. The incorporation of climate variables through ARIMAX demonstrated that rainfall and the number of rainy days significantly influenced coconut production, while temperature, humidity, and wind speed exhibited weaker effects. To improve model stability and avoid multicollinearity, a simplified log-ARIMAX(1,1,1) model was developed by retaining rainfall as the primary exogenous variable. This model achieved the lowest AIC value among the evaluated climate-based models, indicating improved parsimony and explanatory capability. Forecasting results for 2025–2029 indicate a moderate and continuous increase in coconut production. Although ARIMA provides superior predictive accuracy, the rainfall-based ARIMAX model offers additional insights into climate–production relationships, making it valuable for supporting climate-informed forecasting and the future development of early warning frameworks for coconut plantation productivity.
Co-Authors Abdullah Abdullah Herman Farmi Hermiza Mardesci Mulono Apriyanto