Evaluation of Artificial Neural Networks (ANNs) and Multivariate Adaptive Regression Splines (MARS) for Monthly Mean Land Surface Temperature (LST) Modelling– A Case Study of Aowin District, The Republic of Ghana

Authors

  • Michael Stanley Peprah Ihtmoc Consulting Company Limited
  • Edwin Kojo larbi
  • Prince Opoku Appau Ghana Gas Company Limited
  • Michael Angbang Mwin

DOI:

https://doi.org/10.58825/jog.2025.19.1.185

Keywords:

Artificial Intelligence, Back Propagation Neural Network, Multivariate Adaptive Regression Splines, Data Mining, Land Surface Temperature (LST)

Abstract

Accurate and precise estimations of Land Surface Temperature (LST) are essential in climatology, agribusiness, agronomy, urban planning, aviation, and hydrology studies. In this study, the feasibility of two soft computing methods, thus; fifteen different Artificial Neural Network (ANN) architectures and the data mining model of Multivariate Adaptive Regression Splines (MARS) is evaluated for predicting the monthly mean LST of Aowin District, Ghana. Various weather prediction variables, including precipitation, relative humidity, wind speed, and temperature time series historical data spanning 37 years (from 1st January 1985 to 31st December 2022), were used. The data was obtained from a satellite database repository and used in the ANN and MARS models' formulation as input (independent variables) and output (dependent variable), respectively. Five different statistical performance indicators, namely mean error (ME), root mean absolute error (RMAE), mean squared error (MSE), root mean squared error (RMSE), and standard deviation (SD), were used to assess the accuracy and precision of LST estimates from both the ANN and MARS models for the research area. The results demonstrate the capability of both techniques in predicting the monthly mean LST. However, the MARS model produced the best LST estimate, with statistical metrics of ME, RMAE, MSE, RMSE, and SD being 1.8705E-07 °C, 0.0004 °C, 3.3449 °C, 5.7835 °C, and 1.6000E-09 °C, respectively. Both ANN and MARS methods can be effectively applied for LST estimation in the research region and for studying the potential impacts of climate change dynamics globally.

Author Biographies

Edwin Kojo larbi

Technical Officer

CSIR

Kumais, Ghana

Prince Opoku Appau, Ghana Gas Company Limited

process engineer

ghana gas company limited

Accra, Ghana

Michael Angbang Mwin

Geospatial Research Scientist

Tamale, Ghana

References

Adeoti, O. A. and Osanaiye, P. A. (2013), “Effect of Training Algorithms on The Performance of ANN for Pattern Recognition of Bivariate Process”, International Journal of Computer Applications, Vol. 69, No. 20, pp. 8 – 12.

Aowin Suaman District (2006). Aowin Suaman District Assembly: http://aowinsuaman.ghanadistricts.gov.gh

Asafo-Adjei, E., and Buabeng, E. (2016). An Evaluation of Challenges Facing Smallholders in Ghana: A Case Study for the Aowin Suaman District Journal of Biology, Agriculture and Healthcare, Vol.6, No.3, 22-29.

Asenso-Gyambibi, D., Danquah, J. A., Larbi, E. K., Peprah, M. S., and Quaye-Ballard, N. L. (2024). Enhancing Survey Field Data with Artificial Intelligence: A Real-Time Kinematic GPS Study. Arabian Journal of Geosciences, 17(184), 1-12, https://doi.org/10.1007/s12517-024-11989-2.

Azad, H. B., Mekhilef, S., and Gounder, V. (2014). Long-Term Wind Speed Forecasting and General Pattern Recognition using Neural Networks. IEEE Transactions on Sustainable Energy, 5(2), 546-553.

Azari, B., Hassan, K., Pierece, J., and Ebrahimi, S. (2022). Evaluation of Machine Learning Methods Application in Temperature Prediction. Computational Research Progress in Applied Science & Engineering (CRPASE): Transactions of Civil and Environmental Engineering, 8(1), 1-12.

Babacan, H. T., Yuksek, O., and Saka, F. (2022). Performance Evaluation of Artificial Intelligence and Heuristic Regression Methods for Rainfall-Runoff Modelling: An Application in Aksu Stream. Journal of Engineering Science, 11(3), 744-751.

Baghirli O (2015) Comparison of Lavenberg-Marquardt, Scaled Conjugate Gradient and Bayesian Regularization Backpropagation Algorithms for Multistep Ahead Wind Speed Forecasting Using Multilayer Perceptron Feedforward Neural Network. Published MSc Thesis Report, Uppsala University, Gotland, 35 pp.

Beale MH, Hagan MT, Demuth HB (2017) Neural Network Toolbox™ User's Guide. The MathWorks Inc, USA, 431 pp.

Beale EML (1972) A Derivation of Conjugate Gradients. In: Lootsma FA (ed) Numerical methods for nonlinear optimization. Academic Press, London, pp 39–43.

Biglari F, Ebadian A (2015) Limited Memory BFGS Method Based on a High-Order Tensor Model. Comput Optim Appl 60(2):413–422.

Braspenning PJ, Thuijsman F, Weijters AJMM (1995) Artificial Neural Networks: An Introduction to ANN Theory and Practice. Springer Sci Bus Media, 293 pp.

Cadenas, E., and Rivera, W. (2009). Short Term Wind Speed Forecasting in La Venta, Oaxaca, Mexico, using Artificial Neural Networks. Renewal Energy, 34, 274-278.

Cassie, D., St-Hilaire, A., and El-Jabi, N. (2004). Prediction of Water Temperatures using Regression and Stochastic Models, 57th Canadian Water Resources Association Annual Congress, Water and Climate Change: Knowledge for better Adaptation, June 16-18 2004, Montreal, Ql, Canada, 1-6.

Chang, M. H., Chen, W. H., Wu, D. R., Ghorbani, M., Rajendran, S., and Daud, W.M. A. W. (2024). Analysis of Vacuum Operation on Hydrogen Separation from H2/H2O Mixture via Pd Membrane using Taguchi Method, Response Surface Methodology, and Multivariate Adaptive Regression Splines. Energy Conversion and Management: X, 23(100645), 1-15.

Cheng, M. Y., and Cao, M. T. (2014). Accurately Predicting Building Energy Performance using Multivariate Adaptive Regression Splines. Applied Soft Computing, 22, 178-188, http://dx.doi.org/10.1016/j.asoc.2014.05.015.

Deo, R., C., Kisi, O., and Singh, V. P. (2016). Drought Forecasting in Eastern Australia using Multivariate Adaptive Regression Spline, Least Square Support Vector Machine and M5Tree Model. Atmospheric Research, 1-21, http://dx.doi.org/10.1016/j.atmores.2016.10.004

Diaz, J., Fernandez, F. J., and Prieto, M. M. (2020). Hot Metal Temperature Forecasting at Steel Plant using Multivariate Adaptive Regression Splines. Metals, 10(41), 1-16, https://doi.org/10.3390/met10010041.

Dominiak, S., and Terray, P. (2005). Improvement of ENSO Prediction using a Linear Regression Model with a Southern Indian Ocean Sea Surface Temperature Predictor, Geophysical Research Letters, 32(L18702, 1-4.

Dudek, G., 2011. Generalized Regression Neural Network for Forecasting Time Series with Multiple Seasonal Cycles. Springer-Verlag Berlin Heidelberg 1, 1-8.

Ehiakpor, D. S., Danso-Abbeam, G., and Baah, J. E. (2016). Cocoa farmer’s perception on climate variability and its effects on adaptation strategies in the Suaman district of western region, Ghana, Cogent Food & Agriculture, 2:1, 1210557, DOI:10.1080/23311932.2016.1210557

Erdogan, S. (2009). A Comparison of Interpolation Methods for Producing Digital Elevation Models at the Field Scale. Earth Surface Processes and Landforms. 34, 366-376.

Fang, T., and Lahdelma, R. (2016). Evaluation of a Multiple Linear Regression Model and SARIMA Model in Forecasting Heat Demand for District Heating System, Applied Energy, 179, 544-552.

Ferreira, L. B., Duarte, A. B., da Cunha, F. F., and Filho, E. I. F. (2019). Multivariate Adaptive Regression Splines (MARS) Applied to Daily Reference Evapotranspiration Modelling with Limited Weather Data. Acta Scientiarum Agronomy, 41(e39880), 1-11.

Fletcher R, Reeves CM (1964) Function Minimization by Conjugate Gradient. Comput J 7(2):149–154.

Foresee FD, Hagan MT (1997) Gauss-Newton approximation to Bayesian learning. In: Proc Int Jt Conf Neural Netw 1997, Vol 3, pp 1930–1935.

Friedman, J. H. (1991). Multivariate adaptive regression splines”, Annals Statistics, 19, 1-67.

Garcez ASA, Lamb LC, Gabbay DM (2008) Neural-Symbolic Cognitive Reasoning. Springer Sci Bus Media, 198 pp.

Ghana Districts (2017). A repository of all Local Assemblies in Ghana Ghana Districts: A repository of all Local Assemblies in Ghana Accessed: August 25, 2024

Ghana Statistical Service (2010). Population and housing census estimates. Stats Ghana, Accra Ghana. www.ghana statistical service.com

Ghorbani, M. A., Khatibi, R., Fazelifard, M. H., Naghipour, L., and Makarynskyy, O. (2015). Short-Term Wind Speed Predictions with Machine Learning Techniques. Meteoro I Atmos Phys, 1(16), https://doi.org/10.1007/s00703-015-0398-9

Gupta, I., Mittal, H., Rikhari, D., and Singh, A. K. (2022). MLRM: A Multiple Linear Regression Based Model for Average Temperature Prediction of a Day, A Preprint, 1-8, arXiv:2203.05835vI.

Halid, D. A., Atan, I., Jaafar, J., Ashaari, Y., Mohamed, S. N., Samsudin, M. B., and Baki, A. (2018). The Learning of Multivariate Adaptive Regression Splines (MARS) Model in Rainfall-Runoff Processes at Pahang River Catchment. Annals of Valahia University of Targoviste, Geographical Series, 18(2), 161-167.

Hagan MT, Demuth HB, Beale MH (1996) Neural Network Design. PWS Publishing, Boston, MA.

Hannan SA, Manza RR, Ramteke RJ (2010) Generalized Regression Neural Network and Radial Basis Function for Heart Disease Diagnosis. Int J Comput Appl 7(13):7–13.

Hornik K, Stinchcombe M, White H (1989) Multilayer feed forward networks are universal approximators. Neural Netw 2(5):359–366.

Huang FM, Wu P, Ziggah YY (2016) GPS Monitoring Landslide Deformation Signal Processing Using Time Series Model. Int J Signal Process Image Process Pattern Recognit 9(3):321–332.

Ibrahim, M. A. H., Mamat, M. and Leong, W. J. (2014), “The Hybrid BFGS-CG Method in Solving Unconstrained Optimization Problems”, Abstract and Applied Analysis, Vol. 2014, pp. 1 – 6.

Idri A, Zakrani A, Zahi A (2010) Design of Radial Basis Function Neural Networks for Software Effort Estimation. Int J Comput Sci Issue 7(4):11–17.

Ilona (2024). Ancient Origins: The History and Culture of Aowin in Western North Region, Ghana, https://mrcsl.org/aowin/ Accessed: August 26, 2024

Kaloop MR, Rabah M, Hu JW, Zaki A (2017) Using Advanced Soft Computing Techniques for Regional Shoreline Geoid Model Estimation and Evaluation. Mar Georesour Geotechnol 36(6):1–11.

Kaur H, Salaria DS (2013) Bayesian Regularization Based Neural Network Tool for Software Effort Estimation. Glob J Comput Sci Technol 13(2):44–50.

Kişi Ӧ, Uncuoğlu E (2005) Comparison of three back-propagation training algorithm for two case studies. Indian J Eng Mater Sci 12:434–442.

Kumi-Boateng B, Peprah MS (2020) Modeling Local Geometric Geoid using Soft Computing and Classical Techniques: A Case Study of the University of Mines and Technology (UMaT) Local Geodetic Reference Network. Int J Earth Sci Knowl Appl 2(3):166–177.

Kuter, S., Weber, G. W., Akyurek, Z., and Ozmen, A. (2015). Inversion of top of Atmospheric Reflectance Values by Conic Multivariate Adaptive Regression Splines. Inverse Problems in Science and Engineering, 23(4), 651-669.

Kurtulmus, T. O., Yerlikaya-Ozkurt, F., and Askan, A. (2024). Modelling of kappa Factor using Multivariate Adaptive Regression Splines: Application to the Western Turkiye Ground Motion Dataset. Natural Hazards, 120, 7817-7844, https://doi.org/10.1007/s11069-024-06535-y

Lerch, S., and Thorarinsdottir, T. L. (2013). Comparison on non-homogeneous Regression Models for Probabilistic Wind Speed Forecasting. Tellus A: Dynamic Meteorology and Oceanography, 65(1), 21206, 1-14, https://doi.org/10.3402/tellusa.v65i0.21206

Li, D. H. W., Chen, W., Li, S., and Lou, S. (2019). Estimation of Hourly Global Solar Radiation using Multivariate Adaptive Regression Spline (MARS) – A Case Study of Hong Kong. Energy, 115857, 1-31, htttps://doi.org/10.1016/j.energy.2019.115857

Massidda, L., and Marrocu, M. (2017). Use of Multilinear Adaptive Regression Splines and Numerical Weather Prediction to Forecast the Power Output of a PV Plant in Borkum, Germany. Solar Energy, https://doi.org/10.1016/j.solener.2017.02.007

Møller, M. F., 1993. A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks 6(4), 525-533.

Mohandes, M. A., Rehman, S., and Halawani, T. O. (1998). A Neural Networks Approach for Wind Speed Prediction. Renewal Energy, 13(3), 345-354.

Moini, M. and Lakizadeh, A. (2011), Concrete Workability: An Investigation on Temperature Effects Using Artificial Neural Networks, Author House. 148 pp.

Mueller, V. A., and Hemond, F. H. (2013). Extended artificial neural networks: in-corporation of a priori chemical knowledge enables use of ion selective electrodes for in-situ measurement of ions at environmental relevant levels. Talenta. 117: 112-118.

Mukkamala, S., Sung, A. H. and Abraham, A. (2003), “Intrusion Detection Using Ensemble of Soft Computing Paradigms”, In Intelligent Systems Design and Applications, Springer, Berlin, Heidelberg, pp. 239-248.

Mushtaq, K. Z. R., Waris, A., Yang, K., Wang, J., Iqbal, J., and Jameel, M. (2023). Multivariate Wind Power Curve Modelling using Multivariate Adaptive Regression Splines and Regression Trees. PLOS ONE, 18(8): e0290316, 1-25, https://doi.org/10.1317/journal.pone.0290316.

Oduro, S. D., Metia, S., Due, H., Hong, G., and Ha, Q. P. (2015). Multivariate Adaptive Regression Splines model for Vehicular Emission Prediction. Visualization in Engineering, 3(13), 1-12, https://doi.org/10.1186/s40327-015-0024-4

Peprah, M. S., and Larbi, E. K. (2021). Lake Water Level Prediction Model Based on Artificial Intelligence and Classical Techniques – An Empirical Study on Lake Volta Basin, Ghana. International Journal of Earth Sciences Knowledge and Applications, 3(2), 134-150.

Peteiro-Barral, D. and Guijarro-Berdiñas, B. (2013), “A Study on the Scalability of Artificial Neural Networks Training Algorithms Using Multiple-Criteria Decision-Making Methods”, Proceedings of the International Conference on Artificial Intelligence and Soft Computing, Springer, Berlin, Heidelberg, pp. 162-173.

Polak, E. R. and Ribière, G. (1969), “Note Sur la Convergence de Methodes de Directions Conjugat”, Revue Francaise d’Informatique et Recherche Operationnelle, Vol. 16, pp. 35 – 43.

Powell, M. J. D. (1977), “Restart Procedures for the Conjugate Gradient Method”, Mathematical Programming, Vol. 12, No. 1, pp.241-254.

Prasad, N., Singh, R. and Lal, S. P. (2013), “Comparison of Back Propagation and Resilient Propagation Algorithm for Spam Classification”, Proceedings of the 2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation, pp. 29- 34.

Radhika, Y., and Shashi, M. (2009). Atmospheric Temperature Prediction using Support Vector Machines. International Journal of Computer Theory and Engineering, 1(1), 1793-8201.

Raj, N., and Gharineiat, Z. (2021). Evaluation of Multivariate Adaptive Regression Splines and Artificial Neural Network for Prediction of Mean Sea Level Trend Around Northern Australian Coastlines. Mathematics, 9(2696), 1-20, https://doi.org/10.3390/math9212696.

Riedmiller, M. and Braun, H. (1992), “RPROP. A Fast Adaptive Learning Algorithm” Proceedings of the 1992 International Symposium on Computer and Information Sciences, Antalya, Turkey, pp.279-285.

Roy, S. S., Pratyush, C., and Barna, C. (2018). Predicting Ozone Layer Concentration using Multivariate Adaptive Regression Splines, Random Forest and Classification and Regression Tree. Soft Computing Applications, Advances in Intelligent Systems and Computing, 634, https://doi.org/10.1007/978-3-319-62524-9_11

Roy, S. S., Singh, P., Manuja, G., Sikaria, R., and Parekh, M. (2019). Prediction of Airfoil Self-noise using Polynomial Regression, Multivariate Adaptive Regression Splines, Gradient Boosting Techniques and Deep Learning technique. International Journal of Advanced Intelligence Paradigms, X(Y), 1-4.

Sandhu, P.S., Chhabra, S., 2011. A Comparative Analysis of Conjugate Gradient Algorithms and PSO Based Neural Network Approaches for Reusability Evaluation of Procedure Based Software Systems. Chiang Mai Journal of Science 38 (2), 123-135.

Santamaria-Bonfil, G., Reyes-Ballesteros, A., and Gershenson, C. (2016). Wind Speed Forecasting for Wind Farms: A Method Based on Support Vector Regression. Renewal Energy, 85, 790-809.

Soman, S. S., Zareipour, H., Malik, O., and Mandal, P. (2010). A Review of Wind Power and Wind Speed Forecasting Methods with Different Time Horizons. IEEE Xplore, 1-8, https://doi.org/10.1109/NAPS.2010.5619586

Specht, D., 1991. A General Regression Neural Network. IEEE Transactions on Neural Networks 2 (6), 568-576.

Srichandan, S. (2012). A New Approach of Software Effort Estimation using Radial Basis Function Neural Networks. ISSN (Print). 1 (1): 2319-2526.

Sumi, S. M., Zaman, M. F., and Hirose, H. (2012). A Rainfall Forecasting Method using Machine Learning Models and its Application to Fukuoka City Case. International Journal of Applied mathematics and Computer Science, 1-13.

Sreehari, E., and Pradeep Ghantasala, G. S. (2019). Climate Changes Prediction using Simple Linear Regression, Journal of Computational and Theoretical Nanoscience, 16, 1-4.

Szymanowski, M., Kryza, M., and Spallek, W. (2013). Regression-baes Air Temperature Spatial Prediction Models: An Example from Poland. Meteorologische Zeitschrift, 22(5), 577-585.

Yakubu, I., Ziggah, Y. Y., and Peprah, M. S. (2018). Adjustment of DGPS Data using Artificial Intelligence and Classical Least Squares Techniques. Journal of Geomatics, 12(1), 13-20.

Zarinkamar, R. T., and Mayorga, R. V. (2021). Outdoor Relative Humidity Prediction via Machine Learning Techniques. Journal of Environmental Informatics Letters, 6(2), 114-124.

Zhang, G., Bateni, S. M., Jun, C., Khoshkam, H., Band, S. S., and Mosavi, A. (2022). Feasibility of Random Forest and Multivariate Adaptive Regression Splines for Predicting Long-Term Mean Monhtly Dew Point Temperature. Frontiers in Environmental Sciences, 10(826165), 1-12, https://doi.org/10.3389/fenvs.2022.826165

Downloads

Published

2025-04-30

How to Cite

[1]
M. S. Peprah, E. K. Larbi, P. O. Appau, and M. A. Mwin, “Evaluation of Artificial Neural Networks (ANNs) and Multivariate Adaptive Regression Splines (MARS) for Monthly Mean Land Surface Temperature (LST) Modelling– A Case Study of Aowin District, The Republic of Ghana”, Journal of Geomatics, vol. 19, no. 1, pp. 49–68, Apr. 2025.