Automated airborne pest monitoring – a novel technological approach to monitor Drosophila suzukii

J. Fahrentrapp; J. Kambor-Prieur; P. Roosjen; L. Kooistra; D. R. Green; B. J. Gregory

doi:10.17660/ActaHortic.2021.1314.40

Automated airborne pest monitoring – a novel technological approach to monitor Drosophila suzukii

J. Fahrentrapp^*, J. Kambor-Prieur, P. Roosjen, L. Kooistra, D. R. Green, B. J. Gregory

^*Corresponding author for this work

Geography & Environment

Research output: Contribution to journal › Article › peer-review

Abstract

Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.

Original language	English
Pages (from-to)	321-328
Number of pages	8
Journal	Acta Horticulturae
Volume	1314
DOIs	https://doi.org/10.17660/ActaHortic.2021.1314.40
Publication status	Published - 1 Jun 2021

Bibliographical note

Funding Information:
This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: ?????????, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE. ?). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields.

Funding Information:
This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: 627000782, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE.7). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields.

Keywords

Agriculture
Deep learning
Pest monitoring
SWD
UAV

Access to Document

10.17660/ActaHortic.2021.1314.40Licence: Unspecified

Cite this

@article{50a5699cbfd648eea64991bd49f08b70,

title = "Automated airborne pest monitoring – a novel technological approach to monitor Drosophila suzukii",

abstract = "Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.",

keywords = "Agriculture, Deep learning, Pest monitoring, SWD, UAV",

author = "J. Fahrentrapp and J. Kambor-Prieur and P. Roosjen and L. Kooistra and Green, {D. R.} and Gregory, {B. J.}",

note = "Funding Information: This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: ?????????, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE. ?). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields. Funding Information: This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: 627000782, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE.7). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields.",

year = "2021",

month = jun,

day = "1",

doi = "10.17660/ActaHortic.2021.1314.40",

language = "English",

volume = "1314",

pages = "321--328",

journal = "Acta Horticulturae",

issn = "0567-7572",

publisher = "International Society for Horticultural Science",

}

TY - JOUR

T1 - Automated airborne pest monitoring – a novel technological approach to monitor Drosophila suzukii

AU - Fahrentrapp, J.

AU - Kambor-Prieur, J.

AU - Roosjen, P.

AU - Kooistra, L.

AU - Green, D. R.

AU - Gregory, B. J.

N1 - Funding Information: This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: ?????????, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE. ?). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields. Funding Information: This work was supported by ERA net Coordinated Integrated Pest Management in Europe, C-IPM, project “Automated Airborne Pest Management AAPM of Drosophila suzukii in Crops and natural habitats” and the Swiss Federal Office of Agriculture grant: 627000782, in the UK Defra, and by the Netherlands Organisation for Scientific Research (NWO) (project number ALW.FACCE.7). We thank the farmers for providing their fields for the experiments and the students for collecting data in fields.

PY - 2021/6/1

Y1 - 2021/6/1

N2 - Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.

AB - Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.

KW - Agriculture

KW - Deep learning

KW - Pest monitoring

KW - SWD

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=85109789228&partnerID=8YFLogxK

U2 - 10.17660/ActaHortic.2021.1314.40

DO - 10.17660/ActaHortic.2021.1314.40

M3 - Article

AN - SCOPUS:85109789228

SN - 0567-7572

VL - 1314

SP - 321

EP - 328

JO - Acta Horticulturae

JF - Acta Horticulturae

ER -

Automated airborne pest monitoring – a novel technological approach to monitor Drosophila suzukii

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this