Development of Crop-Weather Models Using Gaussian Process Regression for the Prediction of Paddy Yield in Sri Lanka

Full Text (PDF, 719KB), PP.52-65

Views: 0 Downloads: 0

Author(s)

Piyal Ekanayake 1,* Lasini Wickramasinghe 2 Jeevani W. Jayasinghe 2

1. Department of Mathematical Sciences, Faculty of Applied Sciences, Wayamba University of Sri Lanka, Kuliyapitiya, 60200, Sri Lanka

2. Department of Electronics, Faculty of Applied Sciences, Wayamba University of Sri Lanka, Kuliyapitiya, 60200, Sri Lanka

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2022.04.05

Received: 10 Jan. 2022 / Revised: 22 Feb. 2022 / Accepted: 8 Mar. 2022 / Published: 8 Aug. 2022

Index Terms

Gaussian Process Regression, Kernel Function, Machine Learning, Modeling, Yield Prediction

Abstract

This research introduces machine learning models using the Gaussian Process Regression (GPR) depicting the association between paddy yield and weather in Sri Lanka. All major regions in the island with most contribution to the total paddy production were considered in this research. The climatic factors of rainfall, relative humidity, minimum temperature, maximum temperature, average wind speed, evaporation, and sunshine hours were considered as input (independent) variables, while the paddy yield was the output (dependent) variable. The collinearity within each pair of independent and dependent variables was determined using Spearman’s and Pearson’s correlation coefficients. Data sets corresponding to the two main annual paddy cultivation seasons since 2009 were trained in MATLAB to develop crop-weather models. The most appropriate Kernel function was chosen from among four types of Kernels viz. Rational Quadratic, Exponential, Squared Exponential, and Matern 5/2 based on their degree of coherence in modeling. This approach exploits the full potential of GPR in developing highly accurate crop-weather models. The performance of the crop-weather models was measured by the Correlation Coefficient, Mean Absolute Percentage Error, Mean Squared Error, Root Mean Squared Error Ratio, Nash Number and the BIAS. All the GPR-based models proposed in this paper are highly accurate in terms of the aforementioned evaluation metrics. Accordingly, when the climatic data are known or projected, the paddy yield and thereby the harvest of Sri Lanka can be predicted precisely by using the proposed crop-weather models.

Cite This Paper

Piyal Ekanayake, Lasini Wickramasinghe, Jeevani W. Jayasinghe, "Development of Crop-Weather Models Using Gaussian Process Regression for the Prediction of Paddy Yield in Sri Lanka", International Journal of Intelligent Systems and Applications(IJISA), Vol.14, No.4, pp.52-65, 2022. DOI:10.5815/ijisa.2022.04.05

Reference

[1]Juan Cao et al., “Integrating Multi-Source Data for Rice Yield Prediction across China using Machine Learning and Deep Learning Approaches,” Agricultural and Forest Meteorology, vol. 297, pp. 108275, 2021, “doi:10.1016/j.agrformet.2020.108275”.
[2]U. K. Dey, A. H. Masud, and M. N. Uddin, “Rice Yield Prediction Model using Data Mining,” In 2017 International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox's Bazar, Bangladesh, 321-326, (2017), “doi:10.1109/ECACE.2017.7912925”.
[3]N. A. Noureldin, M. A. Aboelghar, H. S. Saudy, and A. M. Ali, “Rice Yield Forecasting Models using Satellite Imagery in Egypt,” The Egyptian Journal of Remote Sensing and Space Science, vol. 16, no. 1, pp. 125-131, 2013, “doi:10.1016/j.ejrs.2013.04.005”.
[4]S. I. Na, J. H. Park, and J. K. Park, “Development of Korean Paddy Rice Yield Prediction Model (KRPM) using Meteorological Element and MODIS NDVI,” Journal of the Korean Society of Agricultural Engineers, vol. 54, no. 3, pp. 141-148, 2012, “doi:10.5389/KSAE.2012.54.3.141”.
[5]J. Kim et al., “Rice Yield Prediction in South Korea by using Random Forest,” Korean Journal of Agricultural and Forest Meteorology, vol. 21, no. 2, pp. 75-84, 2019, “doi:10.5532/KJAFM.2019.21.2.75”.
[6]D. Casanova, J. Goudriaan, M. C. Forner, and J. C. M. Withagen, “Rice Yield Prediction from Yield Components and Limiting Factors,” European Journal of Agronomy, vol. 17, no. 1, pp. 41-61, 2002, “doi:10.1016/S1161-0301(01)00137-X”.
[7]N. Gandhi, O. Petkar, and L. J. Armstrong, “Rice Crop Yield Prediction using Artificial Neural Networks,” In 2016 IEEE Technological Innovations in ICT for Agriculture and Rural Development (TIAR), Chennai, India, pp. 105-110, 2016, “doi:10.1109/TIAR.2016.7801222”.
[8]A. K. Mariappan and J. A. B. Das, “A Paradigm for Rice Yield Prediction in Tamilnadu,” In 2017 IEEE Technological Innovations in ICT for Agriculture and Rural Development (TIAR), Chennai, India, pp. 18-21, 2017, “doi:10.1109/TIAR.2017.8273679”.
[9]N. Vadaparthi, G. S. Tejaswini, and N. B. S. Pallavi, “A Novel Approach for Rice Yield Prediction in Andhra Pradesh,” In Advances in Decision Sciences, Image Processing, Security and Computer Vision, vol. 4, pp. 688-692, 2020, “doi:10.1007/978-3-030-24318-0_78”
[10]V. Amaratunga, L. Wickramasinghe, A. Perera, J. Jayasinghe, and U. Rathnayake, “Artificial Neural Network to Estimate the Paddy Yield Prediction using Climatic Data,” Mathematical Problems in Engineering, vol. 2020, 2020, “doi:10.1155/2020/8627824”.
[11]L. Wickramasinghe, R. Weliwatta, P. Ekanayake, and J. Jayasinghe, “Modeling the Relationship between Rice Yield and Climate Variables Using Statistical and Machine Learning Techniques,” Journal of Mathematics, vol. 2021, 2021, “doi:10.1155/2021/6646126”.
[12]M. P. N. M. Dias, C. M. Navaratne, K. D. N. Weerasinghe, and R. H. A. N. Hettiarachchi, “Application of DSSAT Crop Simulation Model to Identify the Changes of Rice Growth and Yield in Nilwala River Basin for Mid-centuries under Changing Climatic Conditions,” Procedia Food Science, vol. 6, no. 2016, pp. 159-163, 2016, “doi: 10.1016/j.profoo.2016.02.039”.
[13]W. R. S. S.Dharmarathna, S. Herath, and S. B. Weerakoon, “Changing the Planting Date as a Climate Change Adaptation Strategy for Rice Production in Kurunegala District, Sri Lanka,” Sustainability Science, vol. 9, no. 1, pp. 103-111, 2014, “doi:10.1007/s11625-012-0192-2”.
[14]A. Chlingaryan, S. Sukkarieh, and B. Whelan, “Machine Learning Approaches for Crop Yield Prediction and Nitrogen Status Estimation in Precision Agriculture: A Review,” Computers and Electronics in Agriculture, vol. 151, no. 2018, pp. 61-69, 2018, “doi: 10.1016/j.compag.2018.05.012”.
[15]Y. S. Shiu and Y. C. Chuang, “Yield Estimation of Paddy Rice based on Satellite Imagery: Comparison of Global and Local Regression Models,” Remote Sensing, vol. 11, no.2, pp. 111, 2019, “doi:10.3390/rs11020111”.
[16]M. K. Mosleh, Q. K. Hassan, and E. H. Chowdhury, “Application of Remote Sensors in Mapping Rice Area and Forecasting its Production: A Review,” Sensors, vol. 15, no. 1, pp. 769-791, 2015, “doi:10.3390/s150100769”.
[17]Y. Vijayalata, V. R. Devi, P. Rohit, and G. R. Kiran, “A Suggestive Model for Rice Yield Prediction and Ideal Meteorological Conditions during Crisis,” International Journal of Scientific & Technology Research, vol. 8, no. 9, pp. 1572-1576, 2019.
[18]R. Fernandez-Beltran, T. Baidar, J. Kang, and F. Pla, “Rice-Yield Prediction with Multi-Temporal Sentinel-2 Data and 3D CNN: A Case Study in Nepal,” Remote Sensing, vol. 13, no. 7, pp. 1391, 2021, “doi:10.3390/rs13071391”.
[19]J. Han et al., “Prediction of Winter Wheat Yield Based on Multi-Source Data and Machine Learning in China,” Remote Sensing, vol. 12, no. 2, pp. 236, 2020, “doi:10.3390/rs12020236”.
[20]J. You, X. Li, M. Low, D. Lobell, and S. Ermon, “Deep Gaussian Process for Crop Yield Prediction based on Remote Sensing Data,” In Thirty-First AAAI conference on artificial intelligence, San Francisco, California, pp. 4559-4565, 2017.
[21]S. Lanka and M. Depārtamēntuva, “The National Atlas of Sri Lanka,” Survey Department, Sri Lanka, 2007.
[22][Online]. Available: https://meteo.gov.lk/. [Accessed: 15-Dec-2021].
[23][Online]. Available: http://www.climate.lk/. [Accessed: 20.12.2021].
[24]A. Ly, M. Marsman and E. J. Wagenmakers, “Analytic Posteriors for Pearson's Correlation Coefficient,” Statistica Neerlandica, vol. 72, no. 1, pp. 4-13, 2018, “doi:10.1111/stan.12111”.
[25]V. S. Konduri, T. J. Vandal, S. Ganguly, and A. R. Ganguly, “Data Science for Weather Impacts on Crop Yield,” Frontiers in Sustainable Food Systems, vol. 4, pp. 52, 2020, “doi:10.3389/fsufs.2020.00052”.
[26]J. Hauke and T. Kossowski, “Comparison of Values of Pearson's and Spearman's Correlation Coefficients on the Same Sets of Data,” Quaestiones Geographicae, vol. 30, no. 2, pp. 87-93, 2011, “doi:10.2478/v10117-011-0021-1”.
[27]A. K. Sharma, Text book of Correlations and Regression, New Delhi, India, Discovery Publishing House, (2005).
[28]Joseph Isabona, Divine O. Ojuh," Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates ", International Journal of Mathematical Sciences and Computing, Vol.7, No.2, pp. 14-23, 2021.
[29]C. E. Rasmussen, and C. K. Williams, Gaussian Processes for Machine Learning, vol. 1, 2006.
[30]C. K. Williams., and C. E. Rasmussen, Gaussian Processes for Machine Learning, Cambridge, MA: MIT press, vol. 2, no. 3, pp. 4, 2006.
[31]N. Zhang, J. Xiong, J. Zhong, and K. Leatham, “Gaussian Process Regression Method for Classification for High-dimensional Data with Limited Samples,” In 2018 Eighth International Conference on Information Science and Technology (ICIST), Cordoba, Granada, and Seville, Spain, pp. 358-363, 2018, “doi:10.1109/ICIST.2018.8426077”.
[32]S. Stajkowski, D. Kumar, P. Samui, H. Bonakdari, and B. Gharabaghi, “Genetic-algorithm-optimized Sequential Model for Water Temperature Prediction,” Sustainability, vol. 12, no. 13, pp. 5374, 2020, “doi:10.3390/su12135374”.
[33]A. Gholami et al., “Uncertainty Analysis of Intelligent Model of Hybrid Genetic Algorithm and Particle Swarm Optimization with ANFIS to Predict Threshold Bank Profile Shape based on Digital Laser Approach Sensing,” Measurement, vol. 121, pp. 294-303, 2018, “doi:10.1016/j.measurement.2018.02.070”.