Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification

<p dir="ltr">Agricultural Remote Sensing has the potential to enhance agricultural monitoring in smallholder economies to mitigate losses. However, its widespread adoption faces challenges, such as diminishing farm sizes, lack of reliable data-sets and high cost related to commercial...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Waleed Khan (9427344) (author)
مؤلفون آخرون: Nasru Minallah (9427338) (author), Madiha Sher (18086492) (author), Mahmood Ali khan (18086495) (author), Atiq ur Rehman (3044409) (author), Tareq Al-Ansari (9872268) (author), Amine Bermak (1895947) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513510283673600
author Waleed Khan (9427344)
author2 Nasru Minallah (9427338)
Madiha Sher (18086492)
Mahmood Ali khan (18086495)
Atiq ur Rehman (3044409)
Tareq Al-Ansari (9872268)
Amine Bermak (1895947)
author2_role author
author
author
author
author
author
author_facet Waleed Khan (9427344)
Nasru Minallah (9427338)
Madiha Sher (18086492)
Mahmood Ali khan (18086495)
Atiq ur Rehman (3044409)
Tareq Al-Ansari (9872268)
Amine Bermak (1895947)
author_role author
dc.creator.none.fl_str_mv Waleed Khan (9427344)
Nasru Minallah (9427338)
Madiha Sher (18086492)
Mahmood Ali khan (18086495)
Atiq ur Rehman (3044409)
Tareq Al-Ansari (9872268)
Amine Bermak (1895947)
dc.date.none.fl_str_mv 2024-03-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0299350
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Advancing_crop_classification_in_smallholder_agriculture_A_multifaceted_approach_combining_frequency-domain_image_co-registration_transformer-based_parcel_segmentation_and_Bi-LSTM_for_crop_classification/26363131
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Agricultural, veterinary and food sciences
Agriculture, land and farm management
Crop and pasture production
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
Agricultural Remote Sensing
Crop Mapping
Bidirectional Long Short-Term Memory (Bi-LSTM)
Crop Classification
Open Source Tools
Smallholder Economies
Deep Learning
dc.title.none.fl_str_mv Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Agricultural Remote Sensing has the potential to enhance agricultural monitoring in smallholder economies to mitigate losses. However, its widespread adoption faces challenges, such as diminishing farm sizes, lack of reliable data-sets and high cost related to commercial satellite imagery. This research focuses on opportunities, practices and novel approaches for effective utilization of remote sensing in agriculture applications for smallholder economies. The work entails insights from experiments using datasets representative of major crops during different growing seasons. We propose an optimized solution for addressing challenges associated with remote sensing-based crop mapping in smallholder agriculture farms. Open source tools and data are used for inter and intra-sensor image registration, with a root mean square error of 0.3 or less. We also propose and emphasize on the use of delineated vegetation parcels through Segment Anything Model for Geospatial (SAM-GEOs). Furthermore a Bidirectional-Long Short-Term Memory-based (Bi-LSTM) deep learning model is developed and trained for crop classification, achieving results with accuracy of more than 94% and 96% for validation sets of two data sets collected in the field, during 2 growing seasons.</p><h2>Other Information</h2><p dir="ltr">Published in: PLOS ONE<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1371/journal.pone.0299350" target="_blank">https://dx.doi.org/10.1371/journal.pone.0299350</a></p>
eu_rights_str_mv openAccess
id Manara2_ef97d69a00d309382dc4515edd3d5a1b
identifier_str_mv 10.1371/journal.pone.0299350
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26363131
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classificationWaleed Khan (9427344)Nasru Minallah (9427338)Madiha Sher (18086492)Mahmood Ali khan (18086495)Atiq ur Rehman (3044409)Tareq Al-Ansari (9872268)Amine Bermak (1895947)Agricultural, veterinary and food sciencesAgriculture, land and farm managementCrop and pasture productionEngineeringGeomatic engineeringInformation and computing sciencesMachine learningAgricultural Remote SensingCrop MappingBidirectional Long Short-Term Memory (Bi-LSTM)Crop ClassificationOpen Source ToolsSmallholder EconomiesDeep Learning<p dir="ltr">Agricultural Remote Sensing has the potential to enhance agricultural monitoring in smallholder economies to mitigate losses. However, its widespread adoption faces challenges, such as diminishing farm sizes, lack of reliable data-sets and high cost related to commercial satellite imagery. This research focuses on opportunities, practices and novel approaches for effective utilization of remote sensing in agriculture applications for smallholder economies. The work entails insights from experiments using datasets representative of major crops during different growing seasons. We propose an optimized solution for addressing challenges associated with remote sensing-based crop mapping in smallholder agriculture farms. Open source tools and data are used for inter and intra-sensor image registration, with a root mean square error of 0.3 or less. We also propose and emphasize on the use of delineated vegetation parcels through Segment Anything Model for Geospatial (SAM-GEOs). Furthermore a Bidirectional-Long Short-Term Memory-based (Bi-LSTM) deep learning model is developed and trained for crop classification, achieving results with accuracy of more than 94% and 96% for validation sets of two data sets collected in the field, during 2 growing seasons.</p><h2>Other Information</h2><p dir="ltr">Published in: PLOS ONE<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1371/journal.pone.0299350" target="_blank">https://dx.doi.org/10.1371/journal.pone.0299350</a></p>2024-03-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1371/journal.pone.0299350https://figshare.com/articles/journal_contribution/Advancing_crop_classification_in_smallholder_agriculture_A_multifaceted_approach_combining_frequency-domain_image_co-registration_transformer-based_parcel_segmentation_and_Bi-LSTM_for_crop_classification/26363131CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/263631312024-03-01T00:00:00Z
spellingShingle Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
Waleed Khan (9427344)
Agricultural, veterinary and food sciences
Agriculture, land and farm management
Crop and pasture production
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
Agricultural Remote Sensing
Crop Mapping
Bidirectional Long Short-Term Memory (Bi-LSTM)
Crop Classification
Open Source Tools
Smallholder Economies
Deep Learning
status_str publishedVersion
title Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
title_full Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
title_fullStr Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
title_full_unstemmed Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
title_short Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
title_sort Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification
topic Agricultural, veterinary and food sciences
Agriculture, land and farm management
Crop and pasture production
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
Agricultural Remote Sensing
Crop Mapping
Bidirectional Long Short-Term Memory (Bi-LSTM)
Crop Classification
Open Source Tools
Smallholder Economies
Deep Learning