Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production
Applying conventional methods for prediction of environmental impacts in agricultural production is not actually applicable because they usually ignore other aspects such as useful energy and economic consequence. As such, this article evaluates intelligent models for exergoenvironmental damage and...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/3/737 |
| _version_ | 1797613984969392128 |
|---|---|
| author | Ashkan Nabavi-Pelesaraei Hassan Ghasemi-Mobtaker Marzie Salehi Shahin Rafiee Kwok-Wing Chau Rahim Ebrahimi |
| author_facet | Ashkan Nabavi-Pelesaraei Hassan Ghasemi-Mobtaker Marzie Salehi Shahin Rafiee Kwok-Wing Chau Rahim Ebrahimi |
| author_sort | Ashkan Nabavi-Pelesaraei |
| collection | DOAJ |
| description | Applying conventional methods for prediction of environmental impacts in agricultural production is not actually applicable because they usually ignore other aspects such as useful energy and economic consequence. As such, this article evaluates intelligent models for exergoenvironmental damage and emissions social cost (ESC) for mushroom production in Isfahan province, Iran, by three machine learning (ML) methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and support vector regression (SVR). Accordingly, environmental life cycle damages, cumulative exergy demand, and ESC are examined by the ReCiPe2016 method for 100 tons of mushroom production after data collection by interview. Exergoenvironmental results reveal that, in human health and ecosystems, direct emissions, and resources and exergy categories, diesel fuel and compost are the main hotspots. Economic analysis also shows that total ESC is about 1035$. Results of ML models indicate that ANN with a 6-8-3 structure is the optimum topology for forecasting outputs. Moreover, a two-level structure of ANFIS has weak results for prediction in comparison with ANN. However, support vector regression (SVR) with an absolute average relative error (AARE) (%) between 0.85 and 1.03 (based on specific unit), a coefficient of determination (R<sup>2</sup>) between 0.989 and 0.993 (based on specific unit), and a root mean square error (RMSE) between 0.003 and 0.011 (based on specific unit) is selected as the best ML model. It is concluded that ML models can furnish comprehensive and applicable exergoenvironmental-economical assessment of agricultural products. |
| first_indexed | 2024-03-11T07:03:14Z |
| format | Article |
| id | doaj.art-28d3a9d7fc7e4e2c990fffcf88b2fd8e |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-11T07:03:14Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-28d3a9d7fc7e4e2c990fffcf88b2fd8e2023-11-17T09:05:27ZengMDPI AGAgronomy2073-43952023-03-0113373710.3390/agronomy13030737Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom ProductionAshkan Nabavi-Pelesaraei0Hassan Ghasemi-Mobtaker1Marzie Salehi2Shahin Rafiee3Kwok-Wing Chau4Rahim Ebrahimi5Department of Mechanical Engineering of Biosystems, Faculty of Agriculture, Razi University, Kermanshah 6714414971, IranDepartment of Agricultural Machinery Engineering, Faculty of Agriculture, University of Tehran, Karaj 141556619, IranDepartment of Agricultural Machinery Engineering, Faculty of Agriculture, University of Tehran, Karaj 141556619, IranDepartment of Agricultural Machinery Engineering, Faculty of Agriculture, University of Tehran, Karaj 141556619, IranDepartment of Civil and Environmental Engineering, Hong Kong Polytechnic University, Kowloon ZS972, Hong KongDepartment of Mechanical Engineering of Biosystems, Faculty of Agriculture, Shahrekord University, Shahrekord 8815713471, IranApplying conventional methods for prediction of environmental impacts in agricultural production is not actually applicable because they usually ignore other aspects such as useful energy and economic consequence. As such, this article evaluates intelligent models for exergoenvironmental damage and emissions social cost (ESC) for mushroom production in Isfahan province, Iran, by three machine learning (ML) methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and support vector regression (SVR). Accordingly, environmental life cycle damages, cumulative exergy demand, and ESC are examined by the ReCiPe2016 method for 100 tons of mushroom production after data collection by interview. Exergoenvironmental results reveal that, in human health and ecosystems, direct emissions, and resources and exergy categories, diesel fuel and compost are the main hotspots. Economic analysis also shows that total ESC is about 1035$. Results of ML models indicate that ANN with a 6-8-3 structure is the optimum topology for forecasting outputs. Moreover, a two-level structure of ANFIS has weak results for prediction in comparison with ANN. However, support vector regression (SVR) with an absolute average relative error (AARE) (%) between 0.85 and 1.03 (based on specific unit), a coefficient of determination (R<sup>2</sup>) between 0.989 and 0.993 (based on specific unit), and a root mean square error (RMSE) between 0.003 and 0.011 (based on specific unit) is selected as the best ML model. It is concluded that ML models can furnish comprehensive and applicable exergoenvironmental-economical assessment of agricultural products.https://www.mdpi.com/2073-4395/13/3/737cumulative exergy demandlife cycle assessmentartificial neural networksupport vector regression |
| spellingShingle | Ashkan Nabavi-Pelesaraei Hassan Ghasemi-Mobtaker Marzie Salehi Shahin Rafiee Kwok-Wing Chau Rahim Ebrahimi Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production Agronomy cumulative exergy demand life cycle assessment artificial neural network support vector regression |
| title | Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production |
| title_full | Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production |
| title_fullStr | Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production |
| title_full_unstemmed | Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production |
| title_short | Machine Learning Models of Exergoenvironmental Damages and Emissions Social Cost for Mushroom Production |
| title_sort | machine learning models of exergoenvironmental damages and emissions social cost for mushroom production |
| topic | cumulative exergy demand life cycle assessment artificial neural network support vector regression |
| url | https://www.mdpi.com/2073-4395/13/3/737 |
| work_keys_str_mv | AT ashkannabavipelesaraei machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction AT hassanghasemimobtaker machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction AT marziesalehi machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction AT shahinrafiee machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction AT kwokwingchau machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction AT rahimebrahimi machinelearningmodelsofexergoenvironmentaldamagesandemissionssocialcostformushroomproduction |