کاربرد رویکرد هوش مصنوعی در مطالعۀ تأثیر محرک های بزرگ مقیاس آب وهوایی بر بارش بلوچستان پاکستان (مقاله علمی وزارت علوم)
درجه علمی: نشریه علمی (وزارت علوم)
آرشیو
چکیده
استان بلوچستان در کشور پاکستان اغلب به دلیل بارندگی کم در معرض خشکسالی های شدید قرار دارد. چندین نوع محرک آب وهوایی بزرگ مقیاس (LSCD) به دلیل تأثیرشان بر بارندگی در سراسر جهان شناخته شده اند، اما در منطقه بلوچستان مطالعاتی در این زمینه وجود ندارد. این مطالعه با هدف شناسایی LSCDهای معنا دار در بلوچستان و بهبود مهارت پیش بینی بارش ماهانه با استفاده از تجزیه و تحلیل مؤلفه اصلی (PCA)، شبکه عصبی مصنوعی (ANN)، شبکه عصبی منظم شده بیزین (BRNN) و تحلیل رگرسیون چندگانه (MRA) انجام شد. LSCDهای 12ماهه مانند Nino-1+2، Nino-3، Nino-3.4، Nino-4، QBO در 30 و 50 هکتوپاسکال (QBOI و QBOII)، دمای سطح دریا (SST)، دمای هوا (T2M)، ارتفاعات ژئوپتانسیل 500 و 850 هکتوپاسکال، سرعت مداری (500U) و نصف النهاری (V500 وV 850)، شار گرمای نهان و محسوس (LHFOL و SHFOL) و رطوبت ویژه در سطح (SSH) بررسی شدند. همچنین از مجموعه داده های سیستم جهانی جمع آوری داده های زمین (GLDAS)، اندازه گیری بارندگی استوایی (TRMM)، MERRA-2، NOAA و HadISST استفاده شد. نتایج نشان داد LSCDهای معنا دار در سطح اطمینان 99% شامل SSH، SST، LHFOL، SHFOL، T2M، U500، Nino-3.4 و Nino-4 بودند. در طول دوره آزمون، در مقایسه با مدل های MR با ضریب همبستگی 0.15 تا 0.49 و مؤلفه های اصلی با ضریب همبستگی 0.16- تا 0.43، مدل های ANN و BRNN به ترتیب مهارت های پیش بینی بهتری با ضرایب همبستگی 0.40 تا 0.74 و 0.34 تا 0.70 داشتند. نتایج بیانگر توان مدل های ANN و BRNN در پیش بینی بارش ماهانه بلوچستان با استفاده از LSCDهای دارای تأخیر است.Investigating the Application of Artificial Intelligence Approaches for Studying the Impacts of Large-Scale Climate Drivers on Precipitation in Balochistan, Pakistan
The Balochistan province of Pakistan is mostly affected by severe drought events due to little amount of precipitation. “Several Large Scale Climate Drivers (LSCDs) are known for their effects on precipitation worldwide but studies in the region are missing; a wide variety of LSCDs and lagged associative information”.The current study aimed to identify the significant LSCDs in the Balochistan province of Pakistan and improve the prediction skill of monthly precipitation by employing the Principal Component Analysis, Artificial Neural Network (ANN), Bayesian Regularization Neural Network (BRNN), and Multiple Regression (MR) Analysis using the 12 months lagged LSCDs such as Nino-1+2, Nino-3, Nino-3.4, Nino-4, QBO at 30 and 50hpa (QBOI and QBOII), Sea Surface Temperature (SST), 2m air temperature (T2M), 500hpa and 850hpa geopotential heights (H500 and H850), 500hpa zonal velocity (U500), 500hpa and 850hpa meridional velocity (V500 and V850), Latent and Sensible Heat Fluxes Over Land (LHFOL and SHFOL), and Surface Specific Humidity (SSH). To collect the data, Global Land Data Assimilation System, Tropical Rainfall Measuring Mission, MERRA-2, NOAA, Freie University Berlin, and HadISST datasets were used. The results of the study showed that significant LSCDs with a 99% confidence level were SSH, SST, LHFOL, SHFOL, T2M, U500, Nino-3.4, and Nino-4. During the test period, compared with MR models of 0.15 to 0.49 and principal components of -0.16 to 0.43, the ANN and BRNN models had better predictive skills with correlation coefficients of 0.40 to 0.74 and 0.34 to 0.70, respectively. It can be concluded that the ANN and BRNN models enable us to predict monthly precipitation in the Balochistan region with lagged LSCDs. Extended Introduction Pakistan is one of the most vulnerable countries due to climate change. According to the Global Climate Risk Index (GCRI) report, with the passage of time, its vulnerability is increasing. The main threats consist of a rise in temperature, irregular patterns of rainfall, a rise in the sea level, and extreme events such as droughts, floods, and heatwaves. Precipitation plays an important role in the economy of Pakistan as an agricultural country that has experienced variations, particularly in a recent couple of decades when a sharp jump in global atmospheric temperatures was noticed. The southern part of Pakistan which comprises the Sindh and Balochistan provinces has an arid climate and is mostly affected by severe drought events due to less amount of rainfall throughout the year as compared to other parts of the country. This study’s main focus is Balochistan province which has a long history of severe droughts and is an important province in terms of agriculture. Less than 250mm is the annual average rainfall received by the region. It is predicted that throughout the 21 st century if adaptation measures are not taken, there will be a continuous increase in droughts and scarcity of water which will adversely affect the lives of people and the economy. Globally, precipitation and droughts are strongly linked with the large-scale climate drivers through atmospheric associations but there are no detailed studies in Balochistan province that consider a wide variety of large-scale climate drivers and their lagged association with precipitation. The main objective of the present study is to identify the significant large-scale climate drivers in the Balochistan province of Pakistan and improve the prediction skill of monthly precipitation by applying the principal component analysis, artificial neural network, Bayesian regularization neural network, and multiple regression analysis considering the lagged association of climate drivers. Methodology In the present study, first, large-scale climate drivers from NOAA HadISST, MERRA-2, and Freie University Berlin in NetCDF files were processed using the ArcGIS model builder along with the precipitation data from GLDAS and TRMM. The data were first normalized in the range of 0 and 1 using the min-max normalization formula. For showing the 12 months’ lagged association between the large-scale climate drivers and precipitation, a cross-correlation method was employed and the heatmaps were created in Origin 2021b software to show significant lagged correlations. Principal component analysis was applied and the variances and Eigenvalues for each of the components were calculated. Multi-layer feed-forward neural network with a back propagation algorithm was used for the prediction of monthly precipitation with the first two PCs in most cases, three and one in some cases as the predictors. Bayesian Regularization Neural Network (BRNN) was applied which is a version of Artificial Neural Networks (ANN) and is a more powerful method as compared to conventional ANN. MATLAB R2015a environment was used for this purpose. Then, Multiple Regression Analysis (MRA) was carried out and was used as a benchmark for comparing ANN and BRNN models using significantly lagged climate indices in one case and in another case the selected PCs. To validate the performance of all developed models, the TRMM dataset was used. Finally, time series graphs and Radar charts were prepared for comparison. Discussions The findings of cross-correlations between monthly precipitation and large-scale climate drivers in Balochistan province showed the most dominant climate drivers as surface specific humidity, sea surface temperature, latent and sensible heat fluxes over land, 500hpa zonal velocity, 2m air temperature, Nino-3.4 and Nino-4, and the highest correlations were noticed for surface specific humidity, sea surface temperature, latent and sensible heat fluxes over land, 500hpa zonal velocity, 2m air temperature. It is noteworthy that in each district, the lagged correlation of maximum climate indices with precipitation was distinct at distinct lags. The multiple regression best models were selected on the basis of no violation of the limits of statistical significance and lower errors. The MLR model’s performance was low in the region where some of the districts had low correlations. The results from ANN and BRNN models showed that the BRNN models were on a lower side than the ANN models with higher values of correlation coefficient showing their capability of finding the pattern and trend of the GLDAS precipitation. The results of the evaluation of the generalization capability of all models on the TRMM dataset showed that both ANN and BRNN models relatively performed well as correlation and error values were closer to each other. Conclusions The results of this study showed that, first, significant LSCDs with 99% confidence level were surface specific humidity (SSH), sea surface temperature (SST), latent and sensible heat fluxes over land (LHFOL and SHFOL), 2m air temperature (T2M), 500hpa zonal velocity (U500), Nino-3.4, and Nino-4. Second, to predict the monthly precipitation using lagged LSCDs and principal components, MR models were developed. MR models’ performance was low. The highest Pearson correlation in MR models during the training set was observed for Musakhel district as 0.65 and during the test as 0.49 for Musakhel and Zhob. In MR-PC models, the highest correlation was recorded for Awaran (0.50) during the training and for Quetta (0.43) during the test. Third, ANN and BRNN models were developed using the selected PC components and gave higher correlations as compared to regression models indicating their capability of finding the pattern and trend of the observations. They generally manifested lower errors and are more reliable for the purpose of prediction in the region. Maximum correlations during training were 0.77 and 0.73 in both ANN and BRNN models, respectively, for the Lasbela district. In the test case, they were 0.74 and 0.70 for Awaran. Their generalization ability was tested on the TRMM dataset. In conclusion, this study divulged the possibility of monthly precipitation prediction using ANN and BRNN and lagged LSCDs for the study region. It is explicit that the response of precipitation to climatic factors is delayed. Comparing the results of the ANN, BRNN, and MLR, it can be concluded that the artificial intelligence approaches such as ANN and BRNN are reliable nonlinear statistical options that can generate similar and in some cases better forecasts and could be useful for the agriculture and water management in the Balochistan region as it is a very important part of Pakistan in terms of agriculture. In the future, this research will be extended by developing the prediction models by including more LSCDs and can be improved by the approaches of genetic algorithm for the best input selection and the use of observed station-based precipitation data sets. Keywords: <em> </em>Artificial Neural Network, Bayesian Regularization Neural Network, LSCD, Multiple Regression Analysis, Precipitation, Sea Surface Temperature, Balochistan Province-Pakistan. References - Aamir, E., & Hassan, I. (2020). The impact of climate indices on precipitation variability in Baluchistan, Pakistan. <em>Tellus A: Dynamic Meteorology and Oceanography</em>, <em>72</em>(1), 1-46. - Adamowski, J., & Sun, K. (2010). Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. <em>Journal of Hydrology</em>, <em>390</em>(1-2), 85–91. - Ahmed, K., Shahid, S., Haroon, S. B., & Xiao-Jun, W. (2015). Multilayer perceptron neural network for downscaling rainfall in arid region: A case study of Baluchistan, Pakistan. <em>Journal of Earth System Sciences</em>, <em>124</em>(6), 1325–1341. - Ailikun, B., & Yasunari, T. (2001). ENSO and Asian summer monsoon: Persistence and transitivity in the seasonal march. <em>Journal of the Meteorological Society of Japan</em>, <em>79</em>(1), 145–159. - Awan, J. A., & Maqbool, O. (2010). Application of artificial neural networks for monsoon rainfall prediction. <em>2010 6th International Conference on Emerging Technologies (ICET)</em>, 27-32. - Beale, M. H., Hagan, M. T., & Demuth, H. B. (2011). <em>Neural network toolbox TM7: User’s guide</em>. (n.p). - Begum, B., Tajbar, S., Khan, B., & Rafiq, L. (2021). Identification of relationships between climate indices and precipitation fluctuation in Peshawar City-Pakistan. <em>Journal of Research in Environmental Earth Sciences</em>, <em>10</em>, 264–278. - Canchala, T., Alfonso-Morales, W., Ceron, W. L., Carvajal-Escobar, Y., & Caicedo-Bravo, E. (2020). Teleconnections between monthly rainfall variability and large-scale climate indices in southwestern Columbia. <em>Water</em>, <em>12</em>(7), 1863. - Chand, A., & Nand, R. (2009). Rainfall prediction using artificial neural network in the south pacific region. <em>2019 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), </em>Melbourne, VIC, Australia, 1-7. - Choubin, B., Khalighi-Sigaroodi, S., Malekian, A., & Kisi, O. (2014). Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. <em>Hydrological Sciences Journal</em>, <em>61</em>(6), 1001-1009. - Davey, M. K., Brookshaw, A., & Ineson, S. (2014). The probability of the impact of ENSO on precipitation and near-surface temperature. <em>Journal of Climate Risk Management</em>,<em> 1</em>, 5–24. - De Silva, T. M., & Hornberger, G. M. (2019). Identifying El Niño-Southern Oscillation influences on rainfall with classification models: Implications for water resource management of Sri Lanka. <em>Journal of Hydrology and Earth System Sciences</em>, <em>23</em>(4), 1905-1929. - Doranalu Chandrashekar, V., Shetty, A., & Patel, G. C. M. (2019). Estimation of monsoon seasonal precipitation teleconnection with El Niño-Southern Oscillation sea surface temperature indices over the Western Ghats of Karnataka, Asia-Pacific. <em>Journal of Atmospheric Sciences</em>, 1-15. Retrieved from: https://doi.org/10.1007/s13143-019-00133-w. - Field, A. (2009). <em>Discovering statistics using SPSS</em>. Third Edition. London: Sage Publication Ltd. - Ghasemiyeh, H., Bazrafshan, O., & Bakhshayesh Manesh, K. (2017). Artificial neural network for monthly rainfall forecasting using teleconnection patterns (case study: Central Plateau Basin of Iran). <em>Journal of Earth Space Physics</em>, <em>43</em>(2), 405-418. - Global, C. (2020). <em>China-Pakistan economic corridor: CPEC, CPIC</em>. Retrieved from: https://www.cpicglobal.com/pakistan-overview/cpec/. - Hossain, I., Rasel, H. M., Imteaz, M. A., & Pourakbar, S. (2015). Effects of climate indices on extreme rainfall in Queensland, Australia. <em>Proceeding of 21st International Congress on Modelling and Simulation, </em>MODSIM. - Iqbal, M. F., & Athar, H. (2018). Variability, trends, and teleconnections of observed precipitation over Pakistan. <em>Journal of Theoretical and Applied Climatology</em>, <em>134</em>(1), 613–632. - Jamro, S., Channa, F. N., Dars, G. H., Ansari, K., & Krakauer, N. Y. (2020). Exploring the evolution of drought characteristics in Balochistan, Pakistan. <em>Journal of </em><em>Applied Sciences</em>, <em>10</em>(3), 913. - Khan, N., Sachindra, D. A., Shahid, S., Ahmed, K., Shiru, M. S., & Nawaz, N. (2020). Prediction of droughts over Pakistan using machine learning algorithms. <em>Journal of </em><em>Advances in Water Resources</em>, <em>139</em>, 103562. - LDAS. (2021). <em>GLDAS: Project Goals</em>. Retrieved from: https://ldas.gsfc.nasa.gov/gldas. - Lee, J. H., & Julien, P. Y. (2016). Teleconnections of the ENSO and South Korean precipitation patterns. <em>Journal of Hydrology</em>, <em>534</em>, 237–250. - Lin, F. J. (2008). Solving multicollinearity in the process of fitting regression model using the nested estimate procedure. <em>Journal of Quality & Quantity</em>, <em>42</em>(3), 417–426. - Li, X., & Ting, M. (2015). Recent and future changes in the Asian monsoon-ENSO relationship: Natural or forced?. <em>Journal of Geophysical Reserach Letters</em>, <em>42</em>(9), 3502-3512. - Maier, H. R., & Dandy, G. C. (2000). Neural networks for the prediction and forecasting of water resources variables: A review of modelling issues and applications. <em>Journal of Environmental Modelling & Software</em>, <em>15</em>(1), 101–124. - Mekanik, F., Imteaz, M. A., Gato-Trinidad, S., & Elmahdi, A. (2013). Multiple regression and Artificial neural network for long-term rainfall forecasting using large scale climate modes. <em>Journal of Hydrology</em>, <em>503</em>, 11–21. - Menke, W., & Menke, J. (2009). <em>Environmental data analysis with MATLAB</em>. First Edition. UK: Elsevier. - Naz, F., Dars, G. H., Ansari, K., Jamro, S., & Krakauer, N. Y. (2020). Drought trends in Balochistan. <em>Water</em>, <em>12</em>(2), 470. - Pachauri, R. K., Allen, M. R., Barros, V. R., Broome, J., Cramer, W., Christ, R., ... & van Ypserle, J. P. (2014). Climate change 2014: Synthesis report. In<em> Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change</em> (eds. Core Writing Team, R. K. Pachauri and L. A. Meyer]. IPCC, Geneva, Switzerland, 151 pp. - Rasul, G., Afzal, M., Zahid, M., & Bukhari, S. A. A. (2012). <em>Climate Change in Pakistan Focused on Sindh Province</em>. Technical Report PMD 25/2012 55, Pakistan Meteorological Department, Islamabad, Pakistan. Retrieved from: https://doi.org/10.13140/2.1.2170.6560. - Shukla, R. P., Tripathi, K. C., Pandey, A. C., & Das, I. M. L. (2011). Prediction of Indian summer monsoon rainfall using Niño indices: A neural network approach. <em>Journal of Atmospheric Research</em>, <em>102</em>(1-2), 99–109. - Taweesin, K., & Seeboonruang, U. (2019). The relationship between the climatic indices and the rainfall fluctuation in the lower central plain of Thailand. <em>International Journal of Innovative Computing, Information and Control</em>, <em>15</em>(1), 107–127. - Ye, L., Jabbar, S. F., Zahra, M. M. A., & Tan, M. L. (2021). Bayesian regularized neural network model development for predicting daily rainfall from sea level pressure data: Investigation on solving complex hydrology problem. <em>Complexity</em>, (Special Issue). Retrieved from: https://doi.org/10.1155/2021/6631564. - Zuecco, F., Facco, P., Hoeser, S. R., Fogli, M. R., Cicciotti, M., Bezzo, P., & Barolo, M. (2020). Troubleshooting an industrial batch process for the manufacturing of specialty chemicals using data analytics. <em>Journal of Computor Aided Chemical Engineering</em>, <em>48</em>, 1129-1134.
تبلیغات
