Prediction of municipal solid waste quantities using a BiLSTM model, and analysis of biogas and electricity generation potential and greenhouse gas impacts: A case study of Şırnak province

Year 2025, Volume: 10 Issue: 3, 647 - 676, 25.09.2025

Ceylan Üren , Edip Taşkesen

https://doi.org/10.58559/ijes.1725711

Abstract

This study focuses on predicting the Municipal Solid Waste (MSW) quantities in Şırnak province for the 2025-2045 period using a BiLSTM deep learning model, and analyzes the related Biogas (methane gas, CH4), Electricity Energy Produciton Potential (EEPP), and Greenhouse Gas (GHG) emissions based on these predictions. The model was developed using a dataset of 12 financial, social, and demographic variables with an 80% training and 20% testing split, implemented in Python with the NumPy library. Trained on data from 2007 to 2024, the model achieved a low Mean Absolute Percentage Error (MAPE) of 3.83% after hyperparameter optimization, with an average MAPE of 7.99% from k-fold cross-validation. MAPE values below 10% indicate high accuracy and reliability. Findings suggest that the MSW amount, approximately 298,090 tons in 2025, will increase to around 825,929 tons by 2045, representing a 63.9% rise driven mainly by rapid urbanization, population growth, and economic development. Using LandGEM software, CH4 production potential was estimated at about 2.47 million m³ in 2025 and 6.86 million m3 in 2045. Assuming 75% effective CH4 collection, 1.85 million m³ and 5.14 million m³ of CH4 could be recovered in 2025 and 2045, respectively. Corresponding electricity generation potentials are 5,157 MWh in 2025 and 14,315 MWh in 2045, with a total of 225,478 MWh predicted over 21 years. The optimal required plant capacity is calculated as 1.63 MW. Additionally, approximately 141,375 tons of CO2 equivalent GHG emissions are expected to be avoided over this period. These results highlight the environmental benefits of replacing fossil fuels with biogas. The study concludes that BiLSTM based MSW predictions provide a reliable tool for waste management and energy planning, supporting sustainable environmental policies and strategic decision making.

Keywords

Deep learning , BiLSTM , Waste , Energy , Environment

Belediye katı atık miktarlarının BiLSTM derin öğrenme modeli kullanılarak tahmin edilmesi ve tahminlere dayalı olarak biyogaz, elektrik üretim potansiyeli ile sera gazı etkilerinin analizi

Abstract

References

• [1] Karak T, Bhagat RM, Bhattacharyya P, Municipal solid waste generation, composition, and management: the world scenario. Critical Reviews in Environmental Science and Technology 2012; 42(15):1509-1630.
• [2] Valavanidis A. Global municipal solid waste (MSW) in crisis: two billion tonnes of MSW every year, a worrying Worldwide environmental problem [Online]. Available: http://chem-tox-ecotox.org/, Accessed: Jan. 17, 2023.
• [3] Singh RP, Tyagi VV, Allen T, Ibrahim MH, Kothari R. An overview for exploring the possibilities of energy generation from municipal solid waste (MSW) in Indian scenario. Renewable and Sustainable Energy Reviews 2011; 15(9):4797-4808.
• [4] Kaur A, Bharti R, Sharma R. Municipal solid waste as a source of energy. Materials Today: Proceedings 2023; 81(Pt 2):904-915.
• [5] Arli F, Celebi N, Salimi K. The role of an ultra-thin carbon layer in enhancing solar water-splitting performance of Z-scheme ZnO@MOF-5/C photoanodes. Colloids Surf A Physicochem Eng Asp 2025; 720(137112):1-14.
• [6] Liu B, Han B, Liang X, Liu Y. Hydrogen production from municipal solid waste: Potential prediction and environmental impact analysis. International Journal of Hydrogen Energy 2024; 52:1445-1456.
• [7] Zheng L, et al. Preferential policies promote municipal solid waste (MSW) to energy in China: Current status and prospects. Renewable and Sustainable Energy Reviews 2014; 36:135-148.
• [8] Hoang AT, et al. Perspective review on Municipal Solid Waste-to-energy route: Characteristics, management strategy, and role in circular economy. Journal of Cleaner Production 2022; 359:131897.
• [9] Asamoah B, Nikiema J, Gebrezgabher S., Odonkor S., Njenga M., A review on production, marketing and use of fuel briquettes, ICRAF, Colombo, Sri Lanka, 2016.
• [10] Malav LC, Yadav K K, Gupta N, Kumar S, Sharma GK, Krishnan S, Rezania S, Kamyab H, Pham QB, Yadav S, Bhattacharyya S, Yadav VK, Bach QV. A review on municipal solid waste as a renewable source for waste-to-energy project in India: Current practices, challenges, and future opportunities. JOURNAL of Cleaner Production 2020; 277:123227.
• [11] Bulbul S, Ertugrul G, Arli F. Investigation of usage potentials of global energy systems. International Advanced Researches and Engineering Journal 2018; 2(1):58-67.
• [12] Dahlquist E, Biomass as Energy Source: Resources, Systems and Applications (Vol. 3). New York: CRC Press, Taylor & Francis Group, 2012.
• [13] ACT Government Recyclopedia, "Landfill gas to energy," Government of the Australian Capital Territory. [Online]. Available: https://www.cityservices.act.gov.au/. Accessed: Jun. 20, 2025.
• [14] Kantar O, Kilimci ZH. Deep learning based hybrid gold index (XAU/USD) direction forecast model. Journal of the Faculty of Engineering and Architecture of Gazi University 2023; 38(2):1117-1128.
• [15] Uyar R, Özdemir D. Deprem şiddet tahmini için derin öğrenme yöntemlerinin karşılaştırılması ve model önerisi. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi 2025; 25(3):522-534.
• [16] Çetin Ö, Isık AH. Derin öğrenme ile güneş enerjisi santrallerinde aylık elektrik üretim tahmini. Mehmet Akif Ersoy Üniversitesi Fen Bilimleri Enstitüsü Dergisi 2022; 13(1):382-387.
• [17] J. Zhang, P. Wang, R. Yan, and R. X. Gao, Long short-term memory for machine remaining life prediction. Journal of Manufacturing Systems 2018; 48(C): 78-86.
• [18] Xu W, Jiang Y, Zhang X, Li Y, Zhang R, Fu G. Using long short-term memory networks for river flow prediction. Hydrology Research 2020; 51(6):1358-1376.
• [19] Song X, Liu Y, Xue L, Wang J, Zhang J, Wang J, Jiang L, Cheng Z. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model. Journal of Petroleum Science and Engineering 2020; 186:106682.
• [20] Hua Y, Zhao Z, Li R, Chen X, Liu Z, Zhang H. Deep learning with long short-term memory for time series prediction. IEEE Communications Magazine 2019; 57(6):114-119.
• [21] Alizadegan H, Rashidi Malki B, Radmehr A, Karimi H, Ilani M A. Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Exploration & Exploitation 2025; 43(1):281-301.
• [22] Hochreiter S. Untersuchungen zu dynamischen neuronalen Netzen (Ph.D. dissertation). Technische Universität München, München, Germany; 1991.
• [23] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997; 9(8):1735-1780.
• [24] Berus Y, Benteşen Yakut Y. Derin Öğrenme (1D-CNN, RNN, LSTM, BiLSTM) ile Enerji Tüketim Tahmini: Diyarbakır AVM Örneği. DÜMF Mühendislik Dergisi 2024; 15(2):311-322.
• [25] Ozbayoglu AM, Gudelek MU, Sezer OB. Deep learning for financial applications: A survey. Applied Soft Computing 2020; 93:106384.
• [26] Li Y, Du G, Xiang Y, Li S, Ma L, Shao D, Wang X, Chen H. Towards Chinese clinical named entity recognition by dynamic embedding using domain-specific knowledge. Journal of Biomedical Informatics 2020; 106:103435.
• [27] Guo J, Liu M, Luo P, Chen X, Yu H, Wei X. Attention-based BILSTM for the degradation trend prediction of lithium battery. Energy Reports 2023; 9(2):655-664.
• [28] KTB, “Şrınak-Genel Bilgiler,” Kültür ve Turizm Bakanlığı Turizm İstatistikleri, Şırnak İl Kültür ve Turizm Müdürlüğü. Accessed: May 18, 2025. [Online].
• [29] TÜİK, “Merkezi Dağıtım Sistemi MEDAS,” Türkiye İstatistik Kurumu. Accessed: Jun. 18, 2025. [Online]. Available: https://biruni.tuik.gov.tr/medas/?locale=tr
• [30] “Faaliyet Raporu,” Şırnak Belediyesi. Accessed: Jun. 19, 2025. [Online]. Available: https://www.sirnak.bel.tr/
• [31] Niu D, Wu F, Dai S, He S, Wu B. Detection of long-term effect in forecasting municipal solid waste using a long short-term memory neural network. Journal of Cleaner Production 2021; 290:125187.
• [32] Gers F A, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural Compu. 2000; 12(10):2451-2471.
• [33] Liu B, Han Z, Li J, Yan B. Comprehensive evaluation of municipal solid waste power generation and carbon emission potential in Tianjin based on Grey Relation Analysis and Long Short Term Memory. Process Safety and Environmental Protection 2022; 168:918-927.
• [34] Liu B, Zhang L, Wang Q. Demand gap analysis of municipal solid waste landfill in Beijing: Based on the municipal solid waste generation. Waste Management 2021; 134:42-51.
• [35] da Silva DG, de M. Meneses AA. Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction. Energy Reports 2023; 10:3315-3334.
• [36] Vu HL, Ng KTW, Richter A, An C. Analysis of input set characteristics and variances on k-fold cross validation for a Recurrent Neural Network model on waste disposal rate estimation. Journal of Environmental Management 2022; 311:114869.
• [37] Xiao S, Dong H, Geng Y, Tian X, Liu C, Li H. Policy impacts on Municipal Solid Waste management in Shanghai: A system dynamics model analysis. Journal of Cleaner Production 2020; 262:121366.
• [38] Shapiro-Bengtsen S, Andersen FM, Münster M, Zou L. Municipal solid waste available to the Chinese energy sector - Provincial projections to 2050. Waste Management 2020; 112:52-65.
• [39] Krause M, Thorneloe S. Landfill Gas Emissions Model (LandGEM) Version 3.1 User Manual and Tool. Washington; 2024.
• [40] Cudjoe D, Han MS, Chen W. Power generation from municipal solid waste landfilled in the Beijing-Tianjin-Hebei region. Energy 2021; 217:119393.
• [41] Sil A, Kumar S, Kumar R. Formulating LandGem model for estimation of landfill gas under Indian scenario. International Journal of Environmental Technology and Management (IJETM) 2014; 17:239-299.
• [42] Ayodele TR, Ogunjuyigbe ASO, Alao MA. Life cycle assessment of waste-to-energy (WtE) technologies for electricity generation using municipal solid waste in Nigeria. Applied Energy 2017; 201:200-218.
• [43] Assamoi B, Lawryshyn Y. The environmental comparison of landfilling vs. incineration of MSW accounting for waste diversion. Waste Management 2012; 32(5):1019-1030.
• [44] Ayodele TR, Ogunjuyigbe ASO, Alao MA. Economic and environmental assessment of electricity generation using biogas from organic fraction of municipal solid waste for the city of Ibadan, Nigeria. Journal of Cleaner Production 2018; 203:718-735.
• [45] Ogunjuyigbe ASO, Ayodele TR, Alao MA. Electricity generation from municipal solid waste in some selected cities of Nigeria: An assessment of feasibility, potential and technologies. Renewable and Sustainable Energy Reviews 2017; 80:149-162.
• [46] IPCC. Energy (2006 IPCC Guidelines for National Greenhouse Gas Inventories Volume 2). Geneva: Intergovernmental Panel on Climate Change; 2006. [Online]. Available: https://www.ipcc-nggip.iges.or.jp/. Accessed: Jun. 21, 2025.
• [47] WNA. Comparison of Lifecycle Greenhouse Gas Emissions of Various Electricity Generation Sources. London: World Nuclear Association; 2011. [Online]. Available: https://world-nuclear.org/. Accessed: Jun. 21, 2025.
• [48] Sak T, Gönen Ç, Kara EE. Niğde ilinde güneş enerjisi santrallerinin yaygınlaştırılması ve sera gazı emisyonlarının azaltılmasının potansiyeli. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 2019; 31(2):327-335.
• [49] Chum H, Faaij A, Moreira J, Berndes G, Dhamija P, Dong H, Gabrielle B, Goss Eng A, Lucht W, Mapako M, Masera Cerutti O, McIntyre T, Minowa T, Pingoud K. Bioenergy. In: Edenhofer O, Pichs-Madruga R, Sokona Y, Seyboth K, Matschoss P, Kadner S, Zwickel T, Eickemeier P, Hansen G, Schlömer S, von Stechow C, editors. IPCC special report on renewable energy sources and climate change mitigation. Cambridge, U.K. and New York, NY, USA: Cambridge University Press; 2011.