WASTE MANAGEMENT

Identification of patterns/profiles and solid waste production prediction in the city of Lisbon. 

 

Objective
To identify patterns to support the prediction of the production of urban waste associated with a variety of context information (e.g. events, climate situation, etc.)


Research question

What is the social and economic profile of the citizens that produce more undifferenciated waste?

What is the predicted quantity of produced undifferenciated waste that have to be collected by the municipality on a weekly basis?

 

Challenge

 

Challenge Brainstorm Session

Image

Data Understanding

 

Undiferentiated waste collection by freight in 114 circuits for 2018 and 2019.

Image
Image

Data preparation

 

From the location of the collection points for each circuit, was elaborated a map with the zones covered by each circuit through Thiessen polygons.

Image

Indiferentiated waste collection by freight in each circuit for 2018 and 2019.

 
Image
Image

Waste collection data was aggregated to the areas that define each circuit, along with the contextual data.

 

Image

Undifferenciated waste production profile

 

Through correlation analysis was identified the profile of undiferentiated waste producers in Lisbon:

  • Families with dependents from younger ages to young adults
  • Residents looking for job
  • Residents with more than 10 years that don’t know to write or read

According whit this profile residents with less education produce more undiferentiated waste. Will be because they recycle less?

 

Modeling

 

To estimate the production of indiferentiated waste on a weekly basis for each circuit several regression alghoritms were trained.

Capturar3

Evaluation: Machine Learning

 

LinearRegression:

  • RMSE: 278370 kg
  • MAE: 213160 kg
  • MAE per capita (anual): 237.14 kg = 0,63 kg per day
  • MAPE: 0.15

Evaluation: Time series

 

Results (ARIMA):

  • Best parameters (2, 0, 4)
  • AIC = 1302,77 kg
Image
Image
Image

Evaluation

 

  • To assess if the residuals have spatial autocorrelation, Global Moran’s I was computed;
  • The residuals for the OLS model present a clustered pattern;
  • The residuals for the random forest present a random pattern.

Ordinary Least Squares Imagem10

Image

The residuals present a gaussian distribution for KNN and Random forest.

 

Random forest regressor

Imagem11

Image
Image
  • To test another approach a clustering was made based on the maximization of the distances of the cumulative distibution function (cdf) of the waste weight of each circuit through;
  • Kolmogorov – Smirnov test;
  • Three clusters (distributions) were identified.

without clustering

 
Image

clustering

Image

To test another approach a clustering was made based on the maximization of the distances of the density function of the waste weight of each circuit through Kolmogorov – Smirnov test


The clusters were used as explanatory variables along with the variables: number of families with two or more unemoployed; comercial buildings; cluster 0; cluster 1

Capturar6

There was a substantial increase in performace for OLS (0,37 to 0,6).

Literature review

 

  • Abbasi, M. & Abduli, M. A., 2013. Forecasting Municipal Solid waste Generation by Hybrid Support Vector Machine and Partial Least Square Model. Int. J. Environ. Res, 7(1), pp. 27-38.
  • Ali Abdoli, M., Falah Nezhad, M., Salehi Sede, R. & Behboudian, S., 2012. Longterm forecasting of solid waste generation by the artificial neural networks. Environmental Progress and Sustainable Energy, 12, 31(4), pp. 628-636.
  • Al-Khatib, I. A. et al., 2015. Public perception of hazardousness caused by current trends of municipal solid waste management. Waste Management, 1 2, Volume 36, pp. 323-330.
  • Anilkumar, P. & Chithra, K., 2016. Land Use Based Modelling of Solid Waste Generation for Sustainable Residential Development in Small/Medium Scale Urban Areas. Procedia Environmental Sciences, Volume 35, pp. 229-237.
  • Biswas, A. & De, A. K., 2016. A Fuzzy Goal Programming Approach for Solid Waste Management Under Multiple Uncertainties. Procedia Environmental Sciences, Volume 35, pp. 245-256.
  • Hazra, I. T., 2017. Prediction of municipal solid waste generation for developing countries in temporal scale: A fuzzy inference system approach, s.l.: s.n.
  • Intharathirat, R., Abdul Salam, P., Kumar, S. & Untong, A., 2015. Forecasting of municipal solid waste quantity in a developing country using multivariate grey models. Waste Management, 1 5, Volume 39, pp. 3-14.
  • Kannangara, M., Dua, R., Ahmadi, L. & Bensebaa, F., 2018. Modeling and prediction of regional municipal solid waste generation and diversion in Canada using machine learning approaches. Waste Management, 1 4, Volume 74, pp. 3-15.
  • Kolekar, K., Hazra, T. & Chakrabarty, S., 2016. A Review on Prediction of Municipal Solid Waste Generation Models. Procedia Environmental Sciences, Volume 35, pp. 238-244.
  • Lebersorger, S. & Beigl, P., 2011. Municipal solid waste generation in municipalities: Quantifying impacts of household structure, commercial waste and domestic fuel. Waste Management, 9, 31(9-10), pp. 1907-1915.
  • Oribe-Garcia, I. et al., 2015. Identification of influencing municipal characteristics regarding household waste generation and their forecasting ability in Biscay. Waste Management, 1 5, Volume 39, pp. 26-34.
  • Pan, A., Yu, L. & Yang, Q., 2019. Characteristics and forecasting of municipal solid waste generation in China. Sustainability (Switzerland), 1 3.11(5).
  • Prades, M., Gallardo, A. & Ibàñez, M. V., 2015. Factors determining waste generation in Spanish towns and cities. Environmental Monitoring and Assessment, 20 11.187(1).
  • Rimaityte, I. et al., 2012. Application and evaluation of forecasting methods for municipal solid waste generation in an Eastern-European city. Waste Management and Research, 1, 30(1), pp. 89-98.
  • Solano Meza, J. K., Orjuela Yepes, D., Rodrigo-Ilarri, J. & Cassiraga, E., 2019. Predictive analysis of urban waste generation for the city of Bogotá, Colombia, through the implementation of decision trees-based machine learning, support vector machines and artificial neural networks. Heliyon, 1 11.5(11).
  • Song, J. et al., 2014. Simulated annealing based hybrid forecast for improving daily municipal solid waste generation prediction. Scientific World Journal, Volume 2014.
  • Soni, U., Roy, A., Verma, A. & Jain, V., 2019. Forecasting municipal solid waste generation using artificial intelligence models—a case study in India. SN Applied Sciences, 2.1(2).
  • Town, J., Sudan JEWM, S., Lomeling, D. & Wani Kenyi, S., s.d. Forecasting weekly SW generation using ANNs and ARMA models in Forecasting solid waste generation in Juba Town, South Sudan using Artificial Neural Networks (ANNs) and Autoregressive Moving Averages (ARMA), s.l.: s.n.
  • Verma, A., Kumar, A. & Singh, N. B., 2019. Application of Multi Linear Model for Forecasting Municipal Solid Waste Generation in Lucknow City: A Case Study. Current World Environment, 31 12, 14(3), pp. 421-432.
  • Vieira, V. H. d. M. & Matheus, D. R., 2018. The impact of socioeconomic factors on municipal solid waste generation in São Paulo, Brazil. Waste Management and Research, 1 1, 36(1), pp. 79-85.
  • Xu, L., Gao, P., Cui, S. & Liu, C., 2013. A hybrid procedure for MSW generation forecasting at multiple time scales in Xiamen City, China. Waste Management, 6, 33(6), pp. 1324-1331.
  • Xu, L. et al., 2016. Path analysis of factors influencing household solid waste generation: a case study of Xiamen Island, China. Journal of Material Cycles and Waste Management, 1 4, 18(2), pp. 377-384.
  • Younes, M. K. et al., 2015. Solid waste forecasting using modified ANFIS modeling. Journal of the Air and Waste Management Association, 3 10, 65(10), pp. 1229-1238.