Hybrid linear time series approach for long term forecasting of crop yield

Alam, Wasi; Sinha, Kishore; Kumar, Rajeev Ranjan; Ray, Mrinmoy; Rathod, Santosha; Singh, K. N.; Arya, Prawin

doi:10.56093/ijas.v88i8.82573

Cited by 11 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of the DM test revealed that in two sets (training and testing set) of data, the extreme learning machine intervention model performed better than all other models (Table 8). According to several studies [38][39][40][41][42][43][44] for forecasting time series data in the agricul-tural and related fields, the results showed that AI performed better than the standard ARIMA model, which is in accordance with some previous findings. By considering the MAPE values, a significant difference between the actual and forecasted values can be obtained by the DM test.…”

Section: Discussionsupporting

confidence: 87%

Modeling and Forecasting of Rice Prices in India during the COVID-19 Lockdown Using Machine Learning Approaches

et al. 2022

Self Cite

View full text Add to dashboard Cite

Via national lockdowns, the COVID-19 pandemic disrupted the production and distribution of foodstuffs worldwide, including rice (Oryza sativa L.) production, affecting the prices in India’s agroecosystems and markets. The present study was performed to assess the impact of the COVID-19 national lockdown on rice prices in India, and to develop statistical machine learning models to forecast price changes under similar crisis scenarios. To estimate the rice prices under COVID-19, the general time series models, such as the autoregressive integrated moving average (ARIMA) model, the artificial neural network (ANN) model, and the extreme learning machine (ELM) model, were applied. The results obtained using the ARIMA intervention model revealed that during the COVID-19 lockdown in India, rice prices increased by INR 0.92/kg. In addition, the ELM intervention model was faster, with less computation time, and provided better results vs other models because it detects the nonlinear time series data, along with the intervention variable, which was considered an exogenous variable. The use of forecasting models can be a useful tool in supporting decision makers, especially under unpredictable crises. The study results are of great importance for the national agri-food sector, as they can bolster authorities and policymakers in planning and designing more sustainable interventions in the food market during (inter)national crisis situations.

show abstract

Section: Discussionsupporting

confidence: 87%

Modeling and Forecasting of Rice Prices in India during the COVID-19 Lockdown Using Machine Learning Approaches

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to address this issue, the ANN model was employed to capture the non-linear patterns present in the residuals. The ANN model was configured with appropriate lag lengths for both the input and hidden nodes (Alam et al, 2018). The findings revealed that 6-11-1 and 10-1-1 were the best networks fitted for the arrivals, while the 7-4-1 and 8-4-1 networks were fitted to the price series of Chandigarh and Delhi markets, respectively (Zhang, 2003).…”

Section: Arima-annmentioning

confidence: 99%

Exploring the dynamics of arrivals and prices volatility in onion (Allium cepa) using advanced time series techniques

Shankar,

Chandel,

Gupta

et al. 2023

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

Modeling the arrivals and prices of agricultural commodities is an essential requirement for farmers, consumers, and governmental organizations to make informed decisions. This is particularly important for perishable commodities such as vegetables, where spoilage can lead to significant losses for farmers and have a ripple effect on supply and demand dynamics. Volatility in the arrivals and prices of vegetables like onion is a serious issue affecting the common person in different ways. The study attempts to employ different time series models like the autoregressive integrated moving average (ARIMA), Artificial neural network (ANN), hybrid, and ensemble empirical mode decomposition (EEMD) techniques to analyze the pattern and trend of onions in Chandigarh and Delhi markets. From the results of the study, the amount of volatility in the data was found to range from medium to high among the markets. Decomposition techniques such as EEMD-ARIMA and EEMD-ANN performed better for the study data with the least mean absolute percentage error (MAPE) values, such as 17.74 and 6.78% for arrivals and 9.76 and 10.24% for prices at Chandigarh and Delhi markets, respectively. The EEMD techniques exceled in handling the non-linearity and non-stationarity by decomposing the data into different intrinsic modes and a residual, providing a better understanding of the fluctuation levels of data.

show abstract

“…The networks fitted for the Chandigarh, Delhi, Dehradun and Shimla markets are 11-5-1, 9-9-1, 3-1-1 and 9-3-1. Chandigarh market consumed high (11) lags for the input node whereas the Delhi market consumed high (9) lags for the hidden node (Alam et al, 2018). The parameters of the fitted networks are 66, 100, 6 and 34 respectively.…”

Section: Ann Modelmentioning

confidence: 99%

Comparative Study on Key Time Series Models for Exploring the Agricultural Price Volatility in Potato Prices

Shankar,

Chandel,

Gupta

et al. 2024

Preprint

View full text Add to dashboard Cite

Potatoes are one of the widely consumed staple foods all over the world. The prices of potatoes were more unstable than other agricultural commodities due to factors such as perishability, production uncertainties, and seasonal fluctuations. These factors make it difficult for farmers to manage and predict production levels, resulting in supply and price fluctuations. Therefore, it is essential to develop predictive models that can accurately forecast the pricing of agricultural commodities like potatoes. The study attempted to explore the pattern of potato prices in major markets of northern India using different time series models. The empirical findings indicated positively skewed data distributed with a high instability index. In terms of forecasting accuracy, the EEMD-ANN model exhibited the best performance among the various time series techniques, generating the lowest MAPE values of 9.10%, 12.97%, and 4.27% for the Chandigarh, Delhi, and Shimla markets, respectively. Meanwhile, the EEMD-ARIMA model yielded the most accurate prediction results for the Dehradun market, with a MAPE value of 12.97%. The outcomes of this study offer significant insights to farmers, consumers, and government bodies for making informed decisions regarding the production, consumption, and distribution of potatoes. Moreover, the effectiveness of various time series models in handling complex agricultural price series was also investigated.

show abstract

Hybrid linear time series approach for long term forecasting of crop yield

Cited by 11 publications

References 8 publications

Modeling and Forecasting of Rice Prices in India during the COVID-19 Lockdown Using Machine Learning Approaches

Modeling and Forecasting of Rice Prices in India during the COVID-19 Lockdown Using Machine Learning Approaches

Exploring the dynamics of arrivals and prices volatility in onion (Allium cepa) using advanced time series techniques

Comparative Study on Key Time Series Models for Exploring the Agricultural Price Volatility in Potato Prices

Contact Info

Product

Resources

About