System of monitoring and predicting of fire hazardous conditions of municipal solid waste disposal and accumulation sites during their disposal and transportation

Introduction. Fires at disposal and accumulation sites of municipal solid waste (MSW) during their disposal and transportation occur with sufficient regularity. At present, they are practically not predicted. Their detection in many cases occurs when the burning has spread over significant areas.

Aims and objectives. The aim of the work is to develop a system of monitoring and forecasting of conditions of places of disposal and accumulation of MSW that enables to detect burning areas, to forecast the dynamics of changes in key parameters and to assess fire danger of the objects in question.

Materials and methods. A comparative analysis of monitoring systems for places of disposal and accumulation of MSW was made. It is proved that forecasting methods based on artificial neural networks and machine learning are the most promising for preventing fire-hazardous situations at the examined objects. The stages of the working process in the implementation of machine learning technology are defined.

Results. A system of indicators for assessing the fire hazardous conditions of waste disposal and accumulation sites is developed. A model allowing to forecast the dynamics of change of key parameters and to give an assessment of fire hazard of waste disposal and accumulation sites taking into account the chosen planning horizon on the basis of the data received from sensors is created. The requirements for the model, the tasks to be performed were determined, data gathering and cleaning, labelling, design of attributes were performed. The model was trained and evaluated. A method of anomaly detection based on teacherless learning was justified.

A model was developed that allows detecting combustion spots, including hidden ones, with indication of their location and boundaries, based on the data received from sensors. Characteristics of the main scenarios determining the structure and use of the Smart Site service are presented. Its architecture is described. Benefits of its usage are proved. The developed models are tested.

Conclusion. The application of the “Smart Polygon” service will enable visualization of information about the state of waste disposal sites and forecasting results; generate a report for the polygon for a selected period; provide timely notification and transfer necessary information about the possibility or occurrence of fires; select the best solutions aimed at minimizing fire risk and monitor their effectiveness.

The results of the study will be included as a module in an integrated platform for risk-oriented forecasting, reduction of environmental and fire hazard of disposal sites and accumulation of solid waste.

1. Koroleva L.A., Svidzinskaya G.B., Khaydarov A.G., Ivakhnyuk G.K. Application of the Holt – Winters model and the exergetic method for predicting safe waste management in the Russian Federation. Occupational safety in industry. 2021; 11:34-40. DOI: 10.24000/0409-2961-2021-11-34-40 (rus).

2. Kumar А., Agrawal А. Recent trends in solid waste management status, challenges, and potential for the future Indian cities : a review. Current Research in Environmental Sustainability. 2020; 2:10001. DOI: 10.24000/0409-2961-2021-11-34-40

3. Liao С.-Н., Chiu A. SF Evaluate municipal solid waste management problems using hierarchical framework. Procedia — Social and Behavioral Sciences. 2011; 25:353-362. DOI: 10.1016/j.sbspro.2011.10.554

4. ACRF Analysis of the implementation of measures ensuring the environmental safety of the Russian Federation in terms of the elimination of accumulated damage objects and the formation of a comprehensive system for solid municipal waste management: report on the results of an expert-analytical event. Bulletin of the Accounting Chamber of the Russian Federation. 2020; 9(274):6-43. (rus).

5. Fires and fire safety in 2022 : inform.-analyte. col. Balashikha, Federal State Budgetary Institution VNIIPO of the Ministry of Emergency Situations of Russia. (rus).

6. Jafari N.А., Stark T.D., Thalhamer Т. Spatial and temporal characteristics of elevated temperatures in municipal solid waste landfills. Waste Management. 2016; 59:286-301. DOI: 10.1016/j.wasman.2016.10.052

7. Hanson D., Yeşiller N., Onnen M.T. et al. Development of numerical model for predicting heat generation and temperatures in MSW landfills. Waste Management and Research. 2013; 33(10):1993-2000.

8. Samain S. Development of a subsurface landfill fire risk-index. Masters in Science. USA Rowan University, 2018.

9. Saati T., Kerns K. Analytical planning. Organization of systems / trans. from English. Vachnadze R.G. Moscow, Radio and Communications, 1991. (rus).

10. Titov А., Tumanov А., Timofeev А., Tumanov V., Denisov V. Autonomous safety system for MSW landfills. E3S Web of Conferences. 2020; 161:01043. DOI: 10.1051/conf/202016101043

11. Daugela I., Visockiene J.S., Kumpiene J. Detection and analysis of methane emissions from а landfill using unmanned aerial drone systems and a semiconductor sensors. Detritus. 2020; 10:127-138. DOI: 10.31025/2611-4135/2020.13942

12. Khaydarov A.G., Koroleva L.A., Smirnov A.S. Forecasting the occurrence and spread of underground fires at landfills of solid municipal waste. Scientific and analytical journal “Vestnik SaintPetersburg university of State fire service of EMERCOM of Russia”. 2022; 4:41-50. DOI: 10.1051/conf/202016101043 (rus).

13. Qdaisa Н.А., Shatnaw N. Assessing and predicting landfill surface temperature using remote sensing and an artificial neural network. International Journal of Remote Sensing. 2019; 40(24):9556-9571. DOI: 10.1080/01431161.­2019.1633703

14. Amershi S., Begel A., Bird Ch., Deline R. Software Engineering for Machine Learning : a Case Study. IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE 2019). Montreal, QC, Canada, 2019; 291-300. DOI: 10.1109/ICSE-SEIP.2019.00042

15. Martin J.W., Stark T.D., Thalhamer T., Gerbasi-Graf G.T., Gortner R.E. Detection of aluminum waste reactions and associated waste fires. Journal of Hazardous, Toxic & Radioactive Waste. 2013; 17(3):164-174. DOI :10.1061/(ASCE)HZ.2153-5515.0000171

16. Musilli А. Landfill elevated internal temperature detection and landfill fire index assessment for fire monitoring : theses and dissertations. USA, Rowan University, 2016. URL: https://rdw.rowan.edu/etd/2340/

17. Коroleva L.A., Antoshina T.N., Boyakhchyan A.A., Haidarov A.G., Ivakhnuk G.K. Comparative analysis of methods for determining the flammability of municipal solid waste as railway transport cargo. IOP Conference Series: Earth and Environmental Science. 2021; 938(1):012006. DOI: 10.1088/1755-1315/938/1/012006

18. Manjunatha G.S., Chavan D., Lakshmikanthan P., Singh L., Kumar S., Kumar R. Specific heat and thermal conductivity of municipal solid waste and its effect on landfill fires. Waste Management. 2020; 116:120-130. DOI: 10.1016/j.wasman.2020.07.033

19. Millet I., Saaty T. On the relativity of relative measures-accommodating both rank preservation and rank reversals in the AHP. European Journal of Operational Research. 2000; 121(1):202-212. DOI: 10.1016/j.wasman.2020.07.033

20. Mohsen R. Estimation of Greenhouse Gas Emissions in Municipal Solid Waste Landfills in Ontario Using Mathematical Models and Direct Measurements : dissertation. Canada, University of Guelph, 2019.

21. Zaeimi М.В., Rassafi А.А. Designing an integrated municipal solid waste management system using a fuzzy chance-constrained programming model considering economic and environmental aspects under uncertainty. Waste Management. 2021; 125:268-279. DOI: 10.1016/j.wasman.2021.02.047

22. Koroleva L.A., Podmarkov V.V., Khaydarov A.G. Classification system of solid municipal waste landfill zones by fire hazard. Problems of risk management in the technosphere. 2022; 4(64):31-39. (rus).

23. Lim B., Zohren S. Time-series forecasting with deep learning : a survey. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2021; 379(2194):20200209. DOI: 10.1098/rsta.2020.0209

24. Nassif A.B., Talib M.A., Nasir Q., Dakalbab F.M. Machine Learning for Anomaly Detection : a systematic review. IEEE Access. 2021; 9:78658-78700. DOI: 10.1109/ACCESS.2021.3083060