Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters

Uncrewed Aerial Spray Systems (UASS), commonly called drones, have become an important application technique for plant protection products in Asia and worldwide. As such, environmental variables and spray system parameters influencing spray drift deserve detailed investigations. This study presents...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Science of the total environment 2024-07, Vol.934, p.173213, Article 173213
Hauptverfasser: Goulet-Fortin, Jerome, He, Qianwen, Donaldson, Francis, Gottesbueren, Bernhard, Wang, Guobin, Lan, Yubin, Gao, Beibei, Gan, Weijia, Jiang, Yingnan, Laabs, Volker
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page 173213
container_title The Science of the total environment
container_volume 934
creator Goulet-Fortin, Jerome
He, Qianwen
Donaldson, Francis
Gottesbueren, Bernhard
Wang, Guobin
Lan, Yubin
Gao, Beibei
Gan, Weijia
Jiang, Yingnan
Laabs, Volker
description Uncrewed Aerial Spray Systems (UASS), commonly called drones, have become an important application technique for plant protection products in Asia and worldwide. As such, environmental variables and spray system parameters influencing spray drift deserve detailed investigations. This study presents the data analysis of 114 UASS drift trials conducted between December 2021 and December 2022 in China. Study design was based on the ISO 22866:2005 protocol for spray drift trials and considered different UASS platforms, nozzles, and release heights, and specifically continuously measured weather conditions. The relative importance of the environmental variables and spray system parameters was evaluated by a random forest (RF) feature importance analysis, a Sobol sensitivity analysis and partial dependence plots. This approach was preferred to linear ranking techniques such as ANOVA (analysis of variance) due to the non-linearity of the system. In addition, partial dependence plots are proposed to visualize the relationship between specific input parameters within the system. Drift deposition curves calculated from the 114 trials show good agreement with previous UASS trials reported in the literature. As reported in previous studies, spray drift following UASS applications is lower than for manned aerial vehicles, greater than for ground spray applications, and similar to drift observed from orchard air blast applications. In addition, 9 trials were conducted on corn fields in order to evaluate the potential effect of crop cover on spray drift. Spray drift was observed to be reduced over the cropped soil, suggesting that plant cover might possibly reduce spray drift. These findings could help supporting drift mitigation policies, stewardship advice and product labelling around the world. [Display omitted] •Extensive UASS drift trials to evaluate spray drift. Spray drift appears lower than for manned aerial vehicles.•Combined random forest and variance-based sensitivity analysis to evaluate the impact of spray system and environmental variables.•Findings can support drift mitigation policies, stewardship advice, and product labeling worldwide.
doi_str_mv 10.1016/j.scitotenv.2024.173213
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3153614912</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0048969724033606</els_id><sourcerecordid>3055892221</sourcerecordid><originalsourceid>FETCH-LOGICAL-c350t-2a864bf94a4ad68c2ee183df5b29ff2e182e74e7e9c0ede9f21fe6b9af8dd8bc3</originalsourceid><addsrcrecordid>eNqFkc1u3CAUhVHUKplM8woty248BfwH3Y2itKkUqYs0a4ThkjKy8RQYR36dPmlxnGYbNgjxnXOu7kHoEyU7Smjz5bCL2qUxgZ92jLBqR9uS0fIMbShvRUEJa96hDSEVL0Qj2gt0GeOB5NNyeo4uSt7WpC3FBv29mVR_Usn5RxyPQc3YBGcTtmEc8IPXAZ7A4D0Ep3p8_wzczzHBEL_iPR6U_u084B5U8IuF8gZPKsNeQ9GpmLURfHTJTS7N-Vv1c3QRjxbn0V0Y_QA-ZetFuObHZ3t8VEENkCDED-i9VX2Eq5d7ix6-3fy6vi3ufn7_cb2_K3RZk1QwxZuqs6JSlTIN1wyA8tLYumPCWpYfDNoKWhCagAFhGbXQdEJZbgzvdLlFn1ffYxj_nCAmObiooe-Vh_EUZUnrsqGVoOxtlNQ1F4zlSraoXVEdxhgDWHkMblBhlpTIpUt5kK9dyqVLuXaZlR9fQk7dAOZV97-8DOxXAPJWJgdhMYK8eeMC6CTN6N4M-QebErn1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3055892221</pqid></control><display><type>article</type><title>Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters</title><source>Elsevier ScienceDirect Journals</source><creator>Goulet-Fortin, Jerome ; He, Qianwen ; Donaldson, Francis ; Gottesbueren, Bernhard ; Wang, Guobin ; Lan, Yubin ; Gao, Beibei ; Gan, Weijia ; Jiang, Yingnan ; Laabs, Volker</creator><creatorcontrib>Goulet-Fortin, Jerome ; He, Qianwen ; Donaldson, Francis ; Gottesbueren, Bernhard ; Wang, Guobin ; Lan, Yubin ; Gao, Beibei ; Gan, Weijia ; Jiang, Yingnan ; Laabs, Volker</creatorcontrib><description>Uncrewed Aerial Spray Systems (UASS), commonly called drones, have become an important application technique for plant protection products in Asia and worldwide. As such, environmental variables and spray system parameters influencing spray drift deserve detailed investigations. This study presents the data analysis of 114 UASS drift trials conducted between December 2021 and December 2022 in China. Study design was based on the ISO 22866:2005 protocol for spray drift trials and considered different UASS platforms, nozzles, and release heights, and specifically continuously measured weather conditions. The relative importance of the environmental variables and spray system parameters was evaluated by a random forest (RF) feature importance analysis, a Sobol sensitivity analysis and partial dependence plots. This approach was preferred to linear ranking techniques such as ANOVA (analysis of variance) due to the non-linearity of the system. In addition, partial dependence plots are proposed to visualize the relationship between specific input parameters within the system. Drift deposition curves calculated from the 114 trials show good agreement with previous UASS trials reported in the literature. As reported in previous studies, spray drift following UASS applications is lower than for manned aerial vehicles, greater than for ground spray applications, and similar to drift observed from orchard air blast applications. In addition, 9 trials were conducted on corn fields in order to evaluate the potential effect of crop cover on spray drift. Spray drift was observed to be reduced over the cropped soil, suggesting that plant cover might possibly reduce spray drift. These findings could help supporting drift mitigation policies, stewardship advice and product labelling around the world. [Display omitted] •Extensive UASS drift trials to evaluate spray drift. Spray drift appears lower than for manned aerial vehicles.•Combined random forest and variance-based sensitivity analysis to evaluate the impact of spray system and environmental variables.•Findings can support drift mitigation policies, stewardship advice, and product labeling worldwide.</description><identifier>ISSN: 0048-9697</identifier><identifier>ISSN: 1879-1026</identifier><identifier>EISSN: 1879-1026</identifier><identifier>DOI: 10.1016/j.scitotenv.2024.173213</identifier><identifier>PMID: 38750739</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>air ; analysis of variance ; China ; corn ; Drones ; environment ; Machine learning ; orchards ; plant protection ; Random forest ; Sensitivity analysis ; soil ; Spray drift ; Uncrewed Aerial Spray Systems ; weather</subject><ispartof>The Science of the total environment, 2024-07, Vol.934, p.173213, Article 173213</ispartof><rights>2024 Elsevier B.V.</rights><rights>Copyright © 2024. Published by Elsevier B.V.</rights><rights>Copyright © 2024 Elsevier B.V. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c350t-2a864bf94a4ad68c2ee183df5b29ff2e182e74e7e9c0ede9f21fe6b9af8dd8bc3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0048969724033606$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38750739$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Goulet-Fortin, Jerome</creatorcontrib><creatorcontrib>He, Qianwen</creatorcontrib><creatorcontrib>Donaldson, Francis</creatorcontrib><creatorcontrib>Gottesbueren, Bernhard</creatorcontrib><creatorcontrib>Wang, Guobin</creatorcontrib><creatorcontrib>Lan, Yubin</creatorcontrib><creatorcontrib>Gao, Beibei</creatorcontrib><creatorcontrib>Gan, Weijia</creatorcontrib><creatorcontrib>Jiang, Yingnan</creatorcontrib><creatorcontrib>Laabs, Volker</creatorcontrib><title>Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters</title><title>The Science of the total environment</title><addtitle>Sci Total Environ</addtitle><description>Uncrewed Aerial Spray Systems (UASS), commonly called drones, have become an important application technique for plant protection products in Asia and worldwide. As such, environmental variables and spray system parameters influencing spray drift deserve detailed investigations. This study presents the data analysis of 114 UASS drift trials conducted between December 2021 and December 2022 in China. Study design was based on the ISO 22866:2005 protocol for spray drift trials and considered different UASS platforms, nozzles, and release heights, and specifically continuously measured weather conditions. The relative importance of the environmental variables and spray system parameters was evaluated by a random forest (RF) feature importance analysis, a Sobol sensitivity analysis and partial dependence plots. This approach was preferred to linear ranking techniques such as ANOVA (analysis of variance) due to the non-linearity of the system. In addition, partial dependence plots are proposed to visualize the relationship between specific input parameters within the system. Drift deposition curves calculated from the 114 trials show good agreement with previous UASS trials reported in the literature. As reported in previous studies, spray drift following UASS applications is lower than for manned aerial vehicles, greater than for ground spray applications, and similar to drift observed from orchard air blast applications. In addition, 9 trials were conducted on corn fields in order to evaluate the potential effect of crop cover on spray drift. Spray drift was observed to be reduced over the cropped soil, suggesting that plant cover might possibly reduce spray drift. These findings could help supporting drift mitigation policies, stewardship advice and product labelling around the world. [Display omitted] •Extensive UASS drift trials to evaluate spray drift. Spray drift appears lower than for manned aerial vehicles.•Combined random forest and variance-based sensitivity analysis to evaluate the impact of spray system and environmental variables.•Findings can support drift mitigation policies, stewardship advice, and product labeling worldwide.</description><subject>air</subject><subject>analysis of variance</subject><subject>China</subject><subject>corn</subject><subject>Drones</subject><subject>environment</subject><subject>Machine learning</subject><subject>orchards</subject><subject>plant protection</subject><subject>Random forest</subject><subject>Sensitivity analysis</subject><subject>soil</subject><subject>Spray drift</subject><subject>Uncrewed Aerial Spray Systems</subject><subject>weather</subject><issn>0048-9697</issn><issn>1879-1026</issn><issn>1879-1026</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNqFkc1u3CAUhVHUKplM8woty248BfwH3Y2itKkUqYs0a4ThkjKy8RQYR36dPmlxnGYbNgjxnXOu7kHoEyU7Smjz5bCL2qUxgZ92jLBqR9uS0fIMbShvRUEJa96hDSEVL0Qj2gt0GeOB5NNyeo4uSt7WpC3FBv29mVR_Usn5RxyPQc3YBGcTtmEc8IPXAZ7A4D0Ep3p8_wzczzHBEL_iPR6U_u084B5U8IuF8gZPKsNeQ9GpmLURfHTJTS7N-Vv1c3QRjxbn0V0Y_QA-ZetFuObHZ3t8VEENkCDED-i9VX2Eq5d7ix6-3fy6vi3ufn7_cb2_K3RZk1QwxZuqs6JSlTIN1wyA8tLYumPCWpYfDNoKWhCagAFhGbXQdEJZbgzvdLlFn1ffYxj_nCAmObiooe-Vh_EUZUnrsqGVoOxtlNQ1F4zlSraoXVEdxhgDWHkMblBhlpTIpUt5kK9dyqVLuXaZlR9fQk7dAOZV97-8DOxXAPJWJgdhMYK8eeMC6CTN6N4M-QebErn1</recordid><startdate>20240715</startdate><enddate>20240715</enddate><creator>Goulet-Fortin, Jerome</creator><creator>He, Qianwen</creator><creator>Donaldson, Francis</creator><creator>Gottesbueren, Bernhard</creator><creator>Wang, Guobin</creator><creator>Lan, Yubin</creator><creator>Gao, Beibei</creator><creator>Gan, Weijia</creator><creator>Jiang, Yingnan</creator><creator>Laabs, Volker</creator><general>Elsevier B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7S9</scope><scope>L.6</scope></search><sort><creationdate>20240715</creationdate><title>Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters</title><author>Goulet-Fortin, Jerome ; He, Qianwen ; Donaldson, Francis ; Gottesbueren, Bernhard ; Wang, Guobin ; Lan, Yubin ; Gao, Beibei ; Gan, Weijia ; Jiang, Yingnan ; Laabs, Volker</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c350t-2a864bf94a4ad68c2ee183df5b29ff2e182e74e7e9c0ede9f21fe6b9af8dd8bc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>air</topic><topic>analysis of variance</topic><topic>China</topic><topic>corn</topic><topic>Drones</topic><topic>environment</topic><topic>Machine learning</topic><topic>orchards</topic><topic>plant protection</topic><topic>Random forest</topic><topic>Sensitivity analysis</topic><topic>soil</topic><topic>Spray drift</topic><topic>Uncrewed Aerial Spray Systems</topic><topic>weather</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Goulet-Fortin, Jerome</creatorcontrib><creatorcontrib>He, Qianwen</creatorcontrib><creatorcontrib>Donaldson, Francis</creatorcontrib><creatorcontrib>Gottesbueren, Bernhard</creatorcontrib><creatorcontrib>Wang, Guobin</creatorcontrib><creatorcontrib>Lan, Yubin</creatorcontrib><creatorcontrib>Gao, Beibei</creatorcontrib><creatorcontrib>Gan, Weijia</creatorcontrib><creatorcontrib>Jiang, Yingnan</creatorcontrib><creatorcontrib>Laabs, Volker</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>AGRICOLA</collection><collection>AGRICOLA - Academic</collection><jtitle>The Science of the total environment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Goulet-Fortin, Jerome</au><au>He, Qianwen</au><au>Donaldson, Francis</au><au>Gottesbueren, Bernhard</au><au>Wang, Guobin</au><au>Lan, Yubin</au><au>Gao, Beibei</au><au>Gan, Weijia</au><au>Jiang, Yingnan</au><au>Laabs, Volker</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters</atitle><jtitle>The Science of the total environment</jtitle><addtitle>Sci Total Environ</addtitle><date>2024-07-15</date><risdate>2024</risdate><volume>934</volume><spage>173213</spage><pages>173213-</pages><artnum>173213</artnum><issn>0048-9697</issn><issn>1879-1026</issn><eissn>1879-1026</eissn><abstract>Uncrewed Aerial Spray Systems (UASS), commonly called drones, have become an important application technique for plant protection products in Asia and worldwide. As such, environmental variables and spray system parameters influencing spray drift deserve detailed investigations. This study presents the data analysis of 114 UASS drift trials conducted between December 2021 and December 2022 in China. Study design was based on the ISO 22866:2005 protocol for spray drift trials and considered different UASS platforms, nozzles, and release heights, and specifically continuously measured weather conditions. The relative importance of the environmental variables and spray system parameters was evaluated by a random forest (RF) feature importance analysis, a Sobol sensitivity analysis and partial dependence plots. This approach was preferred to linear ranking techniques such as ANOVA (analysis of variance) due to the non-linearity of the system. In addition, partial dependence plots are proposed to visualize the relationship between specific input parameters within the system. Drift deposition curves calculated from the 114 trials show good agreement with previous UASS trials reported in the literature. As reported in previous studies, spray drift following UASS applications is lower than for manned aerial vehicles, greater than for ground spray applications, and similar to drift observed from orchard air blast applications. In addition, 9 trials were conducted on corn fields in order to evaluate the potential effect of crop cover on spray drift. Spray drift was observed to be reduced over the cropped soil, suggesting that plant cover might possibly reduce spray drift. These findings could help supporting drift mitigation policies, stewardship advice and product labelling around the world. [Display omitted] •Extensive UASS drift trials to evaluate spray drift. Spray drift appears lower than for manned aerial vehicles.•Combined random forest and variance-based sensitivity analysis to evaluate the impact of spray system and environmental variables.•Findings can support drift mitigation policies, stewardship advice, and product labeling worldwide.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>38750739</pmid><doi>10.1016/j.scitotenv.2024.173213</doi></addata></record>
fulltext fulltext
identifier ISSN: 0048-9697
ispartof The Science of the total environment, 2024-07, Vol.934, p.173213, Article 173213
issn 0048-9697
1879-1026
1879-1026
language eng
recordid cdi_proquest_miscellaneous_3153614912
source Elsevier ScienceDirect Journals
subjects air
analysis of variance
China
corn
Drones
environment
Machine learning
orchards
plant protection
Random forest
Sensitivity analysis
soil
Spray drift
Uncrewed Aerial Spray Systems
weather
title Evaluating spray drift from Uncrewed Aerial Spray Systems: A machine learning and variance-based sensitivity analysis of environmental and spray system parameters
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T01%3A00%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Evaluating%20spray%20drift%20from%20Uncrewed%20Aerial%20Spray%20Systems:%20A%20machine%20learning%20and%20variance-based%20sensitivity%20analysis%20of%20environmental%20and%20spray%20system%20parameters&rft.jtitle=The%20Science%20of%20the%20total%20environment&rft.au=Goulet-Fortin,%20Jerome&rft.date=2024-07-15&rft.volume=934&rft.spage=173213&rft.pages=173213-&rft.artnum=173213&rft.issn=0048-9697&rft.eissn=1879-1026&rft_id=info:doi/10.1016/j.scitotenv.2024.173213&rft_dat=%3Cproquest_cross%3E3055892221%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3055892221&rft_id=info:pmid/38750739&rft_els_id=S0048969724033606&rfr_iscdi=true