A novel machine learning approach for rice yield estimation

Lingwal, Surabhi; Bhatia, Komal Kumar; Singh, Manjeet

doi:10.1080/0952813x.2022.2062458

Cited by 12 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 9 compares the results of this research with those of the existing literature, emphasizing the novel aspects and advancements of this research in comparison to previous publications. (6) 98% accuracy RFE-SVR (8) R^2-0.710, and RMSE-0.645 Random forest method (9) R-0.933 CNN model (10) R-0.81, RMSE-0.64, MAE-0.50 Proposed Random Forest with FFS algorithm RMSE-59.33 and 99.53% accuracy.…”

Section: Resultsmentioning

confidence: 99%

“…Utilizing feature selection without evaluating its value: This group of studies has utilized a variety of feature selection algorithms to develop crop yield forecasting. In 2019, Lingwal et al (6) utilized various methods to select the ten relevant attributes out of 18 agricultural and weather-related factors that accurately predict paddy yield in Punjab State, India.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Crop Yield Prediction Models with Optimization-Based Feature Selection and Filtering Approaches

Mehla,

Deora,

Dalal

2024

IJST

View full text Add to dashboard Cite

Objective:To analyze the impact of various factors on crop yield and provide insights for improving crop production in the region. Methods: This research employs feature selection algorithms, machine learning models, and feature extraction algorithm Principal Component Analysis (PCA) technique to identify the key factors affecting crop yield in India. Data from the Indian Meteorological, Statistical, and Agriculture Departments spanning five decades are analyzed to provide valuable insights to policymakers and farmers. This research analyzed 20 factors in determining their impact on crop yield in the Indian economy. Three feature selection algorithms were used to identify the essential factors: forward feature selection, backward feature selection, and recursive feature elimination. These three algorithms were used to select the most important factors from the Twenty selected factors, and then three ML models were used to estimate the accuracy of the feature selection algorithms: Random Forest, XGBoost, and Multiple Linear Regression. Principal Component Analysis (PCA) was used for the dimensionality reduction of the features. RMSE, MAPE, MAE, and R2 were used to measure the feature selection method's performance. Findings: Out of the three machine learning algorithms, the Random Forest algorithm with the forward feature selection algorithm provided the highest model accuracy of 98.415 percent. Moreover, compare the combination of three machine learning algorithms and different feature selection algorithms. Novelty: Our approach to predicting crop yield is based on a combination of Feature Selection, PCA, and Machine Learning algorithms. This proposed research utilizes Feature Selection algorithms to identify the most crucial features among 20 available options and then apply Machine Learning models to make accurate predictions based on these features.https://www.indjst.org/

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Crop Yield Prediction Models with Optimization-Based Feature Selection and Filtering Approaches

Mehla,

Deora,

Dalal

2024

IJST

View full text Add to dashboard Cite

show abstract

“…This technique can be used in two common ways: (1) develop different training algorithms, followed by combining all the models (or several models that perform best). This approach has been used for developing prediction models (e.g., [9,19,73,74]);…”

Section: Evaluation: Strengths and Limitationsmentioning

confidence: 99%

“…Regarding the first group, various feature selection algorithms have been adopted to build a crop yield forecasting model. For example, Lingwal et al [9] used the regularized random forest algorithm (RRF; [10]), correlation-based feature selection (CBFS; [11]), and the recursive feature elimination algorithm (RFE; [12]) to select the 10 most significant features from 18 attributes related to agriculture and weather for rice yield prediction in the Punjab State of India. Fernandes et al [13] employed the wrapper method to exclude 14 irrelevant and/or redundant features from the initial dataset to predict sugarcane yield in São Paulo State, Brazil, based on the normalized difference vegetation index (NDVI).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Three Feature Dimension Reduction Techniques for Machine Learning-Based Crop Yield Prediction Models

Pham

Awange

Kühn

2022

Sensors

View full text Add to dashboard Cite

Machine learning (ML) has been widely used worldwide to develop crop yield forecasting models. However, it is still challenging to identify the most critical features from a dataset. Although either feature selection (FS) or feature extraction (FX) techniques have been employed, no research compares their performances and, more importantly, the benefits of combining both methods. Therefore, this paper proposes a framework that uses non-feature reduction (All-F) as a baseline to investigate the performance of FS, FX, and a combination of both (FSX). The case study employs the vegetation condition index (VCI)/temperature condition index (TCI) to develop 21 rice yield forecasting models for eight sub-regions in Vietnam based on ML methods, namely linear, support vector machine (SVM), decision tree (Tree), artificial neural network (ANN), and Ensemble. The results reveal that FSX takes full advantage of the FS and FX, leading FSX-based models to perform the best in 18 out of 21 models, while 2 (1) for FS-based (FX-based) models. These FXS-, FS-, and FX-based models improve All-F-based models at an average level of 21% and up to 60% in terms of RMSE. Furthermore, 21 of the best models are developed based on Ensemble (13 models), Tree (6 models), linear (1 model), and ANN (1 model). These findings highlight the significant role of FS, FX, and specially FSX coupled with a wide range of ML algorithms (especially Ensemble) for enhancing the accuracy of predicting crop yield.

show abstract

“…The random forest approach was also implemented by (Jiya et al, 2023) in predicting rice yields, resulting in a relative root mean square error value of less than 5%. A hybrid approach combining random forest and neural network algorithms for predicting rice yields has a prediction accuracy of 98% (Lingwal, Bhatia, & Singh, 2024). In research conducted by (Patil, Panpatil, & Kokate, 2022), the prediction results of the K-Nearest Neighbors algorithm outperformed Decision Tree with an accuracy rate of 89.4%.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Analysis of Machine Learning Algorithms for Predicting Paddy Production

Aditya,

Munthe,

Sihombing

2024

SinkrOn

View full text Add to dashboard Cite

For countries with large populations, such as Indonesia, food security is a very important issue. The majority of Indonesia's population depends on rice as their main food, and paddy is one of the most widely cultivated food commodities. The very good and accurate national paddy production prediction results really support decisions regarding national paddy production targets for the coming period. Therefore, to ensure supply and price stability, paddy availability must be predicted. Many studies have used machine learning to predict crop yields. By learning important patterns and relationships from input data, machine learning can combine the advantages of other methods to make better predictions of paddy yields. The aim of this research is to conduct a comparative analysis between three machine learning algorithms, namely, random forest, decision tree, and k-nearest neighbors, in predicting paddy production. To determine which algorithm is the best, a model evaluation is carried out using the coefficient of determination (R2-score), mean absolute error (MAE), and mean squared error (MSE). This research goes through methodological stages, starting from collecting datasets, data preprocessing, training and testing split datasets, applying algorithms, and evaluating the model. From this research, results were obtained for the random forest algorithm with an R2-score of 82.38%, MAE of 261726.20, and MSE of 2.19495E+11. For the decision tree, the R2-score was 79.62%, MAE was 323257.99, and MSE was 2.49304E+11. Meanwhile, k-nearest neighbors obtained an R2-score of 76.25%, MAE of 318433.42, and MSE of 2.90577E+11. The results of this research show that the random forest algorithm is the best for predicting paddy production because it obtains a larger R2-score as well as smaller MAE and MSE results.

show abstract

A novel machine learning approach for rice yield estimation

Cited by 12 publications

References 52 publications

Improving Crop Yield Prediction Models with Optimization-Based Feature Selection and Filtering Approaches

Improving Crop Yield Prediction Models with Optimization-Based Feature Selection and Filtering Approaches

Evaluation of Three Feature Dimension Reduction Techniques for Machine Learning-Based Crop Yield Prediction Models

A Comparative Analysis of Machine Learning Algorithms for Predicting Paddy Production

Contact Info

Product

Resources

About