Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu
Abstract
:1. Introduction
1.1. Background
1.2. Existing Methods—ML Algorithms for Yield Prediction
1.3. Objectives
 To assess the paddy crop yield data from high potential realtime locations.
 To estimate the crop yield prediction using a statistical model (MLR).
 To demonstrate advanced machine learning techniques such BPNNs, RBFNNs, GRNNs, and SVR for crop yield prediction.
 To analyze the adapted machine learning techniques using evaluation metrics such as R^{2}, RMSE, MAE, MSE, MAPE, CV, and NSME.
 To select and recommend the best accurate prediction technique to evaluate the crop yield.
2. Data Collection
 Step 1: Collect the data using available sources.
 Step 2: Distribute the data into two segments: training data (70%) and testing data (30%).
 Step 3: Develop the machine learning model to assess the crop yield.
 Step 4: Predict the crop yield using adapted techniques.
 Step 5: Determine the evaluation metrics for each model.
 Step 6: Recommend the bestrated technique for crop yield using observed outcomes.
3. Methodology
3.1. Statistical Analysis
3.2. Machine Learning Techniques
3.2.1. Support Vector Machine (SVM)
3.2.2. Generalized Regression Neural Network (GRNN)
3.2.3. Radial Basis Functional Neural Network (RBFNN)
3.2.4. Back Propagation Neural Network (BPNN)
4. Model Performance
5. Results and Discussions
5.1. Statistical Analysis
5.2. Machine Learning Techniques
6. Conclusions
 Machine learning algorithms attained exceptionally greater yield prediction accuracy than statistical methodology based on the results of evaluation metrics.
 Among the four machine learning algorithms such as SVM, RBFNN, GRNN, and BPNN, GRNN predicted the yield more precisely.
 R^{2}, RMSE, MAE, MSE, MAPE, CV, and NSME performance metrics of GRNN showed a better scale of 0.9863, 0.2295, 0.1290, 0.0526, 1.3439, 0.0255, and 0.0136, respectively.
 Run time of the GRNN model shows a superior scale of 880 ms, which is comparatively less than that of the other ANN models.
 Compared with other existing models from the literature reports, the R^{2} metrics of the proposed model (GRNN) are improved by 7.53%.
 The absolute yield of Tamilnadu and other Indian states are compared, and it is found that Tamilnadu acquired the highest yield, about 3191 kg/ha, and the same is attained with the proposed GRNN prediction model with higher accuracy.
 It is also concluded that Tamilnadu consists of optimum parameters (rainfall, temperature, and pH value) for paddy cultivation that enable the farmers to attain higher yield.
 The recommended machine learning algorithm, notably GRNN, reduces the risk factor for paddy yield due its superior performance metrics.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
 Feng, P.; Wang, B.; Liu, D.L.; Waters, C.; Yu, Q. Incorporating machine learning with biophysical model can improve the evaluation of climate extremes impacts on wheat yield in southeastern Australia. Agric. For. Meteorol. 2019, 275, 100–113. [Google Scholar] [CrossRef]
 Frei, U.; Sporri, S.; Stebler, O.; Holecz, F. Rice field mapping in Sri Lanka using ERS SAR data. Earth Observ. Q. 1999, 63, 30–35. [Google Scholar]
 Rashid, M.; Bari, B.S.; Yusup, Y.; Kamaruddin, M.A.; Khan, N. A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches with Special Emphasis on Palm Oil Yield Prediction. IEEE Access 2021, 9, 63406–63439. [Google Scholar] [CrossRef]
 Schlenker, W.; Roberts, M.J. Nonlinear temperature effects indicate severe damages to US crop yields under climate change. Proc. Natl. Acad. Sci. USA 2009, 106, 15594–15598. [Google Scholar] [CrossRef] [PubMed] [Green Version]
 Folberth, C.; Baklanov, A.; Balkovič, J.; Skalský, R.; Khabarov, N.; Obersteiner, M. Spatiotemporal downscaling of gridded crop model yield estimates based on machine learning. Agric. For. Meteorol. 2019, 264, 1–15. [Google Scholar] [CrossRef] [Green Version]
 Innes, P.J.; Tan, D.K.Y.; Ogtrop, F.V.; Amthor, J.S. Effects of hightemperature episodes on wheat yields in New South Wales, Australia. Agric. For. Meteorol. 2015, 208, 95–107. [Google Scholar] [CrossRef]
 Lamb, D.W.; Brown, R.B. PA—Precision agriculture. J. Agric. Eng. Res. 2001, 78, 117–125. [Google Scholar] [CrossRef]
 Chlingaryan, A.; Sukkarieh, S.; Whelan, B. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Comput. Electron. Agric. 2018, 151, 61–69. [Google Scholar] [CrossRef]
 Mishra, S.; Mishra, D.; Santra, G.H. Applications of Machine Learning Techniques in Agricultural Crop Production: A Review Paper. Indian J. Sci. Technol. 2016, 9, 1–14. [Google Scholar] [CrossRef]
 Marko, O.; Brdar, S.; Panic, M.; Lugonja, P.; Crnojevic, V. Soybean varieties portfolio optimisation based on yield prediction. Comput. Electron. Agric. 2016, 127, 467–474. [Google Scholar] [CrossRef]
 Sellam, V.; Poovammal, E. Prediction of Crop Yield using Regression Analysis. Indian J. Sci. Technol. 2016, 9, 1–5. [Google Scholar] [CrossRef]
 You, J.; Li, X.; Low, M.; Lobell, D.; Ermon, S. Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data. In Proceedings of the ThirtyFirst AAAI Conference on Artificial Intelligence (AAAI17), San Francisco, CA, USA, 4–9 February 2017. [Google Scholar]
 Gu, J.; Yin, G.; Huang, P.; Guo, J.; Chen, L. An improved back propagation neural network prediction model for subsurface drip irrigation system. Comput. Electr. Eng. 2017, 60, 58–65. [Google Scholar] [CrossRef]
 KosariMoghaddam, A.; Rohani, A.; KosariMoghaddam, L.; EsmaeipourTroujeni, M. Developing a Radial Basis Function Neural Networks to Predict the Working Days for Tillage Operation in Crop Production. Int. J. Agric. Manag. Dev. 2018, 9, 119–133. [Google Scholar]
 Khosla, E.; Dharavath, R.; Priya, R. Crop yield prediction using aggregated rainfallbased modular artificial neural networks and Support vector regression. Environ. Dev. Sustain. 2019, 22, 5687–5708. [Google Scholar] [CrossRef]
 EsfandiarpourBoroujeni, I.; Karimi, E.; Shirani, H.; Esmaeilizadeh, M.; Mosleh, Z. Yield prediction of apricot using a hybrid particle swarm optimizationimperialist competitive algorithm support vector regression (PSOICASVR) method. Sci. Hortic. 2019, 257, 108756. [Google Scholar] [CrossRef]
 Maya Gopal, P.S.; Bhargavi, R. Performance Evaluation of Best Feature Subsets for Crop Yield Prediction Using Machine Learning Algorithms. Appl. Artif. Intell. 2019, 33, 621–642. [Google Scholar] [CrossRef]
 Kim, N.; Ha, K.J.; Park, N.W.; Cho, J.; Hong, S.; Lee, Y.W. A Comparison Between Major Artificial Intelligence Models for Crop Yield Prediction: Case Study of the Midwestern United States, 2006–2015. ISPRS Int. J. GeoInf. 2019, 8, 240. [Google Scholar] [CrossRef] [Green Version]
 Khaki, S.; Wang, L. Crop Yield Prediction Using Deep Neural Networks. Front. Plant Sci. 2019, 10, 621. [Google Scholar] [CrossRef] [Green Version]
 Abdipour, M.; YounessiHmazekhanlu, M.; Ramazani, S.H.R.; Omidi, A.H. Artificial neural networks and multiple linear regression as potential methods for modeling seed yield of safflower (Carthamus tinctorius L.). Ind. Crop. Prod. 2019, 127, 185–194. [Google Scholar] [CrossRef]
 Palanivel, K.; Surianarayanan, C. An Approach for Prediction Of Crop Yield Using Machine Learning And Big Data Techniques. Int. J. Comput. Eng. Technol. 2019, 10, 110–118. [Google Scholar] [CrossRef]
 Cai, Y.; Guan, K.; Lobell, D.; Potgieter, A.B.; Wang, S.; Peng, J.; Xu, T.; Asseng, S.; Zhang, Y.; You, L.; et al. Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches. Agric. For. Meteorol. 2019, 274, 144–159. [Google Scholar] [CrossRef]
 Wang, L.; Wang, P.; Liang, S.; Zhu, Y.; Khan, J.; Fang, S. Monitoring maize growth on the North China Plain using a hybrid genetic algorithmbased backpropagation neural network model. Comput. Electron. Agric. 2020, 170, 105238. [Google Scholar] [CrossRef]
 Abbas, F.; Afzaal, H.; Farooque, A.A.; Tang, S. Crop Yield Prediction through Proximal Sensing and Machine Learning Algorithms. Agronomy 2020, 10, 1046. [Google Scholar] [CrossRef]
 Xiong, Y.; Ohashi, S.; Nakano, K.; Jiang, W.; Takizawa, K.; Iijima, K.; Maniwara, P. Application of the radial basis function neural networks to improve the nondestructive Vis/NIR spectrophotometric analysis of potassium in fresh lettuces. J. Food Eng. 2021, 298, 110417. [Google Scholar] [CrossRef]
 Available online: https://mausam.imd.gov.in/ (accessed on 5 August 2021).
 Available online: https://www.tnagrisnet.tn.gov.in/ (accessed on 5 August 2021).
 Available online: https://tn.data.gov.in/statedepartment/departmenteconomicsandstatistics (accessed on 5 August 2021).
 Piekutowska, M.; Niedbała, G.; Piskier, T.; Lenartowicz, T.; Pilarski, K.; Wojciechowski, T.; Pilarska, A.A.; CzechowskaKosacka, A. The Application of Multiple Linear Regression and Artificial Neural Network Models for Yield Prediction of Very Early Potato Cultivars before Harvest. Agronomy 2021, 11, 885. [Google Scholar] [CrossRef]
 Pandey, A.; Mishra, A. Application of artificial neural networks in yield prediction of potato crop. Russ. Agric. Sci. 2017, 43, 266–272. [Google Scholar] [CrossRef]
 Son, N.T.; Chen, C.F.; Chen, C.R.; Guo, H.Y.; Cheng, Y.S.; Chen, S.L.; Lin, H.S.; Chen, S.H. Machine learning approaches for rice crop yield predictions using timeseries satellite data in Taiwan. Int. J. Remote. Sens. 2020, 41, 7868–7888. [Google Scholar] [CrossRef]
 Granata, F. Evapotranspiration evaluation models based on machine learning algorithms—A comparative study. Agric. Water Manag. 2019, 217, 303–315. [Google Scholar] [CrossRef]
 Han, L.; Yang, G.; Dai, H.; Xu, B.; Yang, H.; Feng, H.; Li, Z.; Yang, X. Modeling maize aboveground biomass based on machine learning approaches using UAV remotesensing data. Plant Methods 2019, 15, 10. [Google Scholar] [CrossRef] [Green Version]
 Ramesh, D.; Vardhan, B.V. Analysis Of Crop Yield Prediction Using Data Mining Techniques. Int. J. Res. Eng. Technol. 2015, 4, 470–473. [Google Scholar]
 Elavarasan, D.; Vincent, P.M.D. Crop yield prediction using deep reinforcement learning model for sustainable agrarian applications. IEEE Access 2020, 8, 8688686901. [Google Scholar]
 Gopal, P.S.M.; Bhargavi, R. A novel approach for efcient crop yield prediction. Comput. Electron. Agric. 2019, 165, 104968. [Google Scholar] [CrossRef]
 Shiu, Y.S.; Chuang, Y.C. Yield estimation of paddy rice based on satellite imagery: Comparison of global and local regression models. Remote Sens. 2019, 11, 111. [Google Scholar] [CrossRef] [Green Version]
 Guo, Y.; Fu, Y.; Hao, F.; Zhang, X.; Wu, W.; Jin, X.; Bryant, C.R.; Senthilnath, J. Integrated phenology and climate in rice yields prediction using machine learning methods. Ecol. Indic. 2021, 120, 106935. [Google Scholar] [CrossRef]
 Elavarasan, D.; Vincent, P.M.D.R.; Srinivasan, K.; Chang, C.Y. A hybrid CFS lter and RFRFE wrapperbased feature extraction for enhanced agricultural crop yield prediction modeling. Agriculture 2020, 10, 400. [Google Scholar] [CrossRef]
 Khaki, S.; Wang, L.; Archontoulis, S.V. A CNNRNN framework for crop yield prediction. Front. Plant Sci. 2020, 10, 1750. [Google Scholar] [CrossRef] [PubMed]
 Yalcin, H. An approximation for a relative crop yield estimate from field images using deep learning. In Proceedings of the 2019 8th International Conference on AgroGeoinformatics (AgroGeoinformatics), Istanbul, Turkey, 16–19 July 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1–6. [Google Scholar]
 Hilal, Y.Y.; Ishak, W.; Yahya, A.; Asha’ari, Z.H. Development of genetic algorithm for optimization of yield models in oil palm production. Chil. J. Agric. Res. 2018, 78, 228–237. [Google Scholar] [CrossRef] [Green Version]
 Nevavuori, P.; Narra, N.; Lipping, T. Crop yield prediction with deep convolutional neural networks. Comput. Electron. Agric. 2019, 163, 104859. [Google Scholar] [CrossRef]
 Government of India. A Status Note on Rice in India, National Food Security Mission. Available online: https://www.nfsm.gov.in (accessed on 5 August 2021).
Ref No  Year  Methodologies  Inferences 

[10]  2016  Weighted histograms regression 

[11]  2016  Regression Analysis (RA) 

[12]  2017  Gaussian process component and spatiotemporal structure 

[8]  2017  Generalized regression neural network and radial basis function neural network 

[13]  2017  Improved genetic algorithmback propagation neural network prediction algorithm 

[8]  2018  Remote sensing and machine learning algorithms 

[14]  2018  Multiple linear regression and radial basis function artificial networks 

[15]  2019  Aggregated rainfallbased modular artificial neural networks and support vector regression 

[16]  2019  Hybrid particle swarm optimization imperialist competitive algorithm, support vector regression 

[17]  2019  Support vector regression, Knearest neighbor, random forest, and artificial neural network 

[18]  2019  Deep neural network (DNN) 

[19]  2019  Deep neural network (DNN) 

[20]  2019  Artificial neural network 

[21]  2019  Machine learning and big data 

[22]  2019  Support vector machine, random forest, and neural network 

[23]  2020  Hybrid genetic algorithmbased backpropagation neural network (GABPNN) model 

[24]  2020  Proximal Sensing (PS) and machine learning algorithms 

[25]  2021  Partial least squares and radial basis function neural network. 

Parameters  Tiruchirappalli  Pudukkottai  Perambalur 

pH range  8.2–9.6  6.8–8.5  8.09–8.6 
Temperature  24–38  24–33  25–34 
Mean annual rainfall  761  821  861 
SW monsoon (June–September): mm  273.3  351.9  270 
NE monsoon (October–December): mm  394.8  394.1  466 
Field  16  21  13 
Variables  Rows  Minimum  Maximum  Mean  Std. Deviation 

Mean Rainfall (mm)  100  266.0  464.0  366.4  75.59 
Temperature (°C)  24.0  38.0  31.5  4.40  
Fertilizer(urea) (kg/ha)  123.50  197.6  166.62  24.86  
Nitrogen (N) (kg/ha)  143.26  197.6  174.13  16.66  
Phosphorus (P)(kg/ha)  44.46  61.75  52.04  4.75  
Potassium (K) (kg/ha)  37.05  54.34  44.48  4.49  
pH value  6.90  8.93  8.12  0.48  
Yeild (kg/ha)  2358.0  3189.0  2773.5  207.7 
Parameters  Descriptions/Values 

Type of SVM model  EpsilonSVR 
SVM kernel function  Radial basis function (RBF) 
Search criterion  Minimize total error 
Number of points evaluated during search  1093 
Minimum error found by search  0.462196 
Epsilon  0.001 
C  34.5930771 
Gamma  0.41179479 
P  0.21545292 
Number of support vectors  73 
Parameters  Ranges/Values 

No. of neurons  25 
Minimum radius  0.019 
Maximum radius  395.265 
Minimum lambda  0.06458 
Maximum lambda  8.64019 
Regularization lambda (final weights)  1.549 × 10^{−5} 
Layer  Neurons  Activation 

Input  7  Pass through 
Hidden  15  Logistic 
Output  1  Linear 
Regression Statistics  
Multiple R  0.942762  
R Square  0.8888  
Adjusted R Square  0.88034  
Standard Error  0.682364  
Observations  100  
ANOVA  
df  SS  MS  F  Significance F  
Regression  7  8.1039  1.15770  105.0487  4.69E–41  
Residual  92  1.0138  0.01102  
Total  99  9.1178  
Coefficients  Standard Error  t Stat  pValue  Lower 95%  Upper 95%  Lower 95.0%  Upper 95.0%  
Intercept  0.439148  0.11923  3.683201  0.000389  0.202347  0.675948  0.202347  0.675948 
Mean Rainfall (mm)  0.04361  0.109511  0.398225  0.691387  −0.17389  0.261109  −0.17389  0.261109 
Temperature (°C)  −0.36972  0.106524  −3.47074  0.000792  −0.58128  −0.15815  −0.58128  −0.15815 
Fertilizer(urea) (kg/ha)  −0.13005  0.092188  −1.41074  0.161694  −0.31314  0.05304  −0.31314  0.05304 
Nitrogen (N) (kg/ha)  0.343809  0.094175  3.650756  0.000434  0.15677  0.530848  0.15677  0.530848 
Phosphorus (P) (kg/ha)  0.112423  0.072317  1.554591  0.123477  −0.0312  0.256051  −0.0312  0.256051 
Potassium (K) (kg/ha)  0.304443  0.079279  3.840153  0.000226  0.146988  0.461897  0.146988  0.461897 
pH value  −0.04314  0.049602  −0.86974  0.386708  −0.14165  0.055373  −0.14165  0.055373 
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. 
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Joshua, V.; Priyadharson, S.M.; Kannadasan, R. Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu. Agronomy 2021, 11, 2068. https://doi.org/10.3390/agronomy11102068
Joshua V, Priyadharson SM, Kannadasan R. Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu. Agronomy. 2021; 11(10):2068. https://doi.org/10.3390/agronomy11102068
Chicago/Turabian StyleJoshua, Vinson, Selwin Mich Priyadharson, and Raju Kannadasan. 2021. "Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu" Agronomy 11, no. 10: 2068. https://doi.org/10.3390/agronomy11102068