Comparative Analysis of the Implementation of Support Vector Machines and Long Short-Term Memory Artificial Neural Networks in Municipal Solid Waste Management Models in Megacities.

The development of methodologies to support decision-making in municipal solid waste (MSW) management processes is of great interest for municipal administrations. Artificial intelligence (AI) techniques provide multiple tools for designing algorithms to objectively analyze data while creating highly precise models. Support vector machines and neuronal networks are formed by AI applications offering optimization solutions at different managing stages. In this paper, an implementation and comparison of the results obtained by two AI methods on a solid waste management problem is shown. Support vector machine (SVM) and long short-term memory (LSTM) network techniques have been used. The implementation of LSTM took into account different configurations, temporal filtering and annual calculations of solid waste collection periods. Results show that the SVM method properly fits selected data and yields consistent regression curves, even with very limited training data, leading to more accurate results than those obtained by the LSTM method.

PWC-based evaluation of groundwater pesticide pollution in the Júcar River Basin.

Predicting pesticides' behavior in the environment is necessary to anticipate and minimize their adverse effects. Despite the use of pesticides in Spain is increasing, the implementation and use of predictive mathematical models is seldomly done in practice due to the lack of available data. In this original work, the Pesticide Root Zone Model version 5 (PRZM 5) mathematical model under the Pesticide in Water Concentration 1.52 (PWC) interface has been applied to model pesticide behavior in nine groundwater bodies located inside the Júcar River Basin (JRB) in Spain. Mathematical modeling allowed calculating the maximum concentration of pesticides after completing the calibration process. Bromacil, terbuthylazine, atrazine, desethyl-terbuthylazine, and terbumeton concentrations in groundwater were simulated between 2006 and 2019. Results show that the maximum pesticide concentration value on every well exceeds the current Spanish Maximum Concentration Limit (0.1 µg/L). PRZM 5 was able to reproduce pesticide concentration observations over time despite the limited amount of available data. This study contributes to assessing environmental risks caused by the use of pesticides inside the JRB and can potentially be applied in other areas of interest.

M-GRCT: A Dynamic Circular Economy Model for the Optimal Design of Waste Management Systems in Low-Income Municipalities.

This article introduces M-GRCT, a circular economy decision support model for the design of recyclable waste management systems in low-income municipalities. The model allows for performing calculations on a set of two scenarios integrating a sociocultural dynamics assessment, this being a characteristic feature of this type of municipalities. The model also integrates the analysis of the remaining variables usually addressed in solid waste management schemes while considering topics such as reduction of the carbon footprint due to activities such as the transport of recyclable waste, the generation of leachates, the generation of greenhouse gases and the promotion of an increase in the number of associated recyclers and selective routes. The economic evaluation of the different implementation scenarios is supported by a dynamic tool called DATA4 (a macro-type array accompanied by two control panels programmed in Visual Basic and dashboards by Power BI). M-GRCT constitutes a tool for the promotion of good environmental practices and the identification of strategies for the promotion of local development mechanisms. Results provided by the model contrast with those obtained by traditional linear economy approaches. An illustrative example of the application of the M-GRCT model is shown. The model was used to simulate the municipal solid waste managing system of the municipality of Guateque (Colombia). The results show the importance of integrating both economic and environmental costs to optimally allocate governmental and private resources when the recycling rate is expected to increase in the next 10 years.

Numerical Modeling of Groundwater Pollution by Chlorpyrifos, Bromacil and Terbuthylazine. Application to the Buñol-Cheste Aquifer (Spain).

Chlorpyrifos, Bromacil and Terbuthylazine are commonly used as insecticides and herbicides to control weeds and prevent non-desirable growth of algae, fungi and bacteria in many agricultural applications. Despite their highly negative effects on human health, environmental modeling of these pesticides in the vadose zone until they reach groundwater is still not being conducted on a regular basis. This work shows results obtained by version 5.08 of the Pesticide Root Zone Model (PRZM5) numerical model to simulate the fate and transport of Chlorpyrifos, Bromacil and Terbuthylazine between 2006 and 2018 inside the Buñol-Cheste aquifer in Spain. The model uses a whole set of parameters to solve a modified version of the mass transport equation considering the combined effect of advection, dispersion and reactive transport processes. The simulation process was designed for a set of twelve scenarios considering four application doses for each pesticide. Results show that the maximum concentration value for every scenario exceeds the current Spanish Maximum Concentration Limit (0.1 µg/L). Numerical simulations were able to reproduce concentration observations over time despite the limited amount of available data.

Assessment of Groundwater Contamination by Terbuthylazine Using Vadose Zone Numerical Models. Case Study of Valencia Province (Spain).

Terbuthylazine is commonly used as an herbicide to control weeds and prevent non-desirable grow of algae, fungi and bacteria in many agricultural applications. Despite its highly negative effects on human health, environmental modeling of this kind of pesticide in the vadose zone till reaching groundwater is still not being done on a regular basis. This work shows results obtained by two mathematical models (PESTAN and PRZM-GW) to explain terbuthylazine behavior in the non-saturated zone of a vertical soil column. One of the models use a one-dimensional analytical formulation to simulate the movement of terbuthylazine through the non-saturated soil to the phreatic surface. The second and more complex model uses a whole set of parameters to solve a modified version of the mass transport equation considering the combined effect of advection, dispersion and reactive transport processes. Both models have been applied as a case-study on a particular location in South Valencia Aquifer (Spain). A whole set of simulation scenarios have been designed to perform a parameter sensitivity analysis. Despite both models leading to terbuthylazine's concentration values, numerical simulations show that PRZM-GW is able to reproduce concentration observations leading to much more accurately results than those obtained using PESTAN.

BIOLEACH: A New Decision Support Model for the Real-Time Management of Municipal Solid Waste Bioreactor Landfills.

This paper introduces BIOLEACH, a new decision support model for the real-time management of municipal solid waste bioreactor landfills that allows estimating the leachate and biogas production. Leachate production is estimated using an adaptation of the water balance equation which considers every hydrological component and the water consumed by anaerobic organic matter degradation to create biogas and the leachate recirculation flows pumped from the landfill pond under a bioreactor management scheme. Landfill gas production is estimated considering the leachate formation process as a coupled effect through the production or consumption of water. BIOLEACH uses waste production and climate data at monthly scale and computes leachate production accounting for the actual conditions inside the waste mass. Biogas production is computed simultaneously, considering the available water to adjust the chemical organic matter biodegradation. BIOLEACH is a valuable bioreactor managing tool as it allows calculating the recirculation volume of leachate that ensures optimal moisture conditions inside the waste mass and therefore maximizing biogas production. As an illustrative example of a BIOLEACH application, the model has been applied to a real landfill located in Murcia Region (Spain) showing the economic and environmental benefits derived from leachate superficial recirculation.

Analytical Methodology for the Identification of Critical Zones on the Generation of Solid Waste in Large Urban Areas.

One of the main environmental issues to address in large urban areas is the ever-increasing generation of municipal solid waste (MSW) and the need to manage it properly. Despite significant efforts having been made to implement comprehensive solid waste management systems, current management methods often do not provide sustainable alternatives which ensure the reduction of solid waste generation. This paper presents an analytical methodology that employs a combination of geographic information system techniques (GIS) along with statistical and numerical optimization methods to evaluate solid waste generation in large urban areas. The methodology was successfully applied to evaluate MSW generation in different exclusive service areas (ASES) of the city of Bogotá (Colombia). The results of the analysis on the solid waste generation data in each collection area in terms of its socioeconomic level are presented below. These socioeconomic levels are explained by defining different strata in terms of their purchasing power. The results demonstrate the usefulness of these GIS and numerical optimization techniques as a valuable complementary tool to analyze and design efficient and sustainable solid waste management systems.

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.

This study presents an analysis of three models associated with artificial intelligence as tools to forecast the generation of urban solid waste in the city of Bogotá, in order to learn about this type of waste's behavior. The analysis was carried out in such a manner that different efficient alternatives are presented. In this paper, a possible decision-making strategy was explored and implemented to plan and design technologies for the stages of collection, transport and final disposal of waste in cities, while taking into account their particular characteristics. The first model used to analyze data was the decision tree which employed machine learning as a non-parametric algorithm that models data separation limitations based on the learning decision rules on the input characteristics of the model. Support vector machines were the second method implemented as a forecasting model. The primary advantage of support vector machines is their proper adjustment to data despite its variable nature or when faced with problems with a small amount of training data. Lastly, recurrent neural network models to forecast data were implemented, which yielded positive results. Their architectural design is useful in exploring temporal correlations among the same. Distribution by collection zone in the city, socio-economic stratification, population, and quantity of solid waste generated in a determined period of time were factors considered in the analysis of this forecast. The results found that support vector machines are the most appropriate model for this type of analysis.