- You are here:
-
-
All publications
- Predicting ammonia emissions from controlled storage of laying-hen manure using two modelling frameworks: deterministic and machine learning
All publications from your selection
Predicting ammonia emissions from controlled storage of laying-hen manure using two modelling frameworks: deterministic and machine learning
Authors: Andr?s F. Gonzalez-Mora, Alain N. Rousseau, Laurence Loyon, Fabrice Guiziou
Identifier: CSBE21180
Download file:
Published in: CSBE-SCGAB Technical Conferences » 5th CIGR and AGM Quebec City 2021 » World Congress on Computers in Agriculture and Natural Resources
Download RAW file:
DOI:
Description: Ammonia emissions (AE) are likely linked to a wide range of environmental and human health issues. Poultry production contributes to AE with emissions coming from in-situ production and manure storage. Thus, manure management practices have become the subject of interest, focusing on reducing N contributions. However, tracking and control AE from commercial laying hen facilities are time and resource-intensive leading to negative consequences for farm economics and workers? welfare. Simulating AE from laying hen manure (LHM) can provide a powerful framework to formulate and analyse control strategies within laying hen housing systems. Using emission data from LHM storage under controlled laboratory conditions, two modelling techniques were employed to simulate ammonia (NH3) concentrations: a mechanistic model based on physicochemical equations (rMM) and a machine learning method known as Random Forest (RF). Objectif functions such as root mean squared error (RMSE) and the coefficient of determination (R2) were applied to measure model performance. The average of NH3 concentrations were 210.5 ? 44.5 mg N m-3. The rMM used in this study did not prove to be a convincing modelling approach with RMSE and R2 values of 80.8 mg N m-3 and 0.50, respectively. Nevertheless, the RF model had a good performance for predicting ammonia concentrations with RMSE and R2 values of 10.9 mg N m-3 and 0.93, respectively, highlighting the potential of using machine learning (ML) tools for environmental tracking in egg production facilities
Keywords:
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2021-06-11
Technical field:
Conference name: 5th CIGR International Conference and CSBE-SCGAB AGM 2021, Quebec City,QC, 11-14 May 2021.
Session name: World Congress on Computers in Agriculture and Natural Resources (WCCA 2)
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage:
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
DOI:
Description: Ammonia emissions (AE) are likely linked to a wide range of environmental and human health issues. Poultry production contributes to AE with emissions coming from in-situ production and manure storage. Thus, manure management practices have become the subject of interest, focusing on reducing N contributions. However, tracking and control AE from commercial laying hen facilities are time and resource-intensive leading to negative consequences for farm economics and workers? welfare. Simulating AE from laying hen manure (LHM) can provide a powerful framework to formulate and analyse control strategies within laying hen housing systems. Using emission data from LHM storage under controlled laboratory conditions, two modelling techniques were employed to simulate ammonia (NH3) concentrations: a mechanistic model based on physicochemical equations (rMM) and a machine learning method known as Random Forest (RF). Objectif functions such as root mean squared error (RMSE) and the coefficient of determination (R2) were applied to measure model performance. The average of NH3 concentrations were 210.5 ? 44.5 mg N m-3. The rMM used in this study did not prove to be a convincing modelling approach with RMSE and R2 values of 80.8 mg N m-3 and 0.50, respectively. Nevertheless, the RF model had a good performance for predicting ammonia concentrations with RMSE and R2 values of 10.9 mg N m-3 and 0.93, respectively, highlighting the potential of using machine learning (ML) tools for environmental tracking in egg production facilities
Keywords:
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2021-06-11
Technical field:
Conference name: 5th CIGR International Conference and CSBE-SCGAB AGM 2021, Quebec City,QC, 11-14 May 2021.
Session name: World Congress on Computers in Agriculture and Natural Resources (WCCA 2)
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage:
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
©
2024
CSBE-SCGAB