Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018. Pouliot, D., Alavi, N., Wilson, S., Duffe, J., Pasher, J., Davidson, A., Daneshfar, B., & Lindsay, E. Remote Sensing, 13(4):634, February, 2021. ![Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018 [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The prairie region of Canada is a dynamically changing landscape in relation to past and present anthropogenic activities and recent climate change. Improving our understanding of the rate, timing, and distribution of landscape change is needed to determine the impact on wildlife populations and biodiversity, ultimately leading to better-informed management regarding requirements for habitat amount and its connectedness. In this research, we assessed the viability of an approach to detect from–to class changes designed to be scalable to the prairie region with the capacity for local refinement. It employed a deep-learning convolutional neural network to model general land covers and examined class memberships to identify land-cover conversions. For this implementation, eight land-cover categories were derived from the Agriculture and Agri-Food Canada Annual Space-Based Crop Inventory. Change was assessed in three study areas that contained different mixes of grassland, pasture, and forest cover. Results showed that the deep-learning method produced the highest accuracy across all classes relative to an implementation of random forest that included some first-order texture measures. Overall accuracy was 4% greater with the deep-learning classifier and class accuracies were more balanced. Evaluation of change accuracy suggested good performance for many conversions such as grassland to crop, forest to crop, water to dryland covers, and most bare/developed-related changes. Changes involving pasture with grassland or cropland were more difficult to detect due to spectral confusion among classes. Similarly, conversion to forests in some cases was poorly detected due to gradual and subtle change characteristics combined with confusion between forest, shrub, and croplands. The proposed framework involved several processing steps that can be explored to enhance the thematic content and accuracy for large regional implementation. Evaluation for understanding connectivity in natural land covers and related declines in species at risk is planned for future research.
@article{pouliot_assessment_2021,
title = {Assessment of {Landsat} {Based} {Deep}-{Learning} {Membership} {Analysis} for {Development} of from–to {Change} {Time} {Series} in the {Prairie} {Region} of {Canada} from 1984 to 2018},
volume = {13},
issn = {2072-4292},
url = {https://www.mdpi.com/2072-4292/13/4/634},
doi = {10.3390/rs13040634},
abstract = {The prairie region of Canada is a dynamically changing landscape in relation to past and present anthropogenic activities and recent climate change. Improving our understanding of the rate, timing, and distribution of landscape change is needed to determine the impact on wildlife populations and biodiversity, ultimately leading to better-informed management regarding requirements for habitat amount and its connectedness. In this research, we assessed the viability of an approach to detect from–to class changes designed to be scalable to the prairie region with the capacity for local refinement. It employed a deep-learning convolutional neural network to model general land covers and examined class memberships to identify land-cover conversions. For this implementation, eight land-cover categories were derived from the Agriculture and Agri-Food Canada Annual Space-Based Crop Inventory. Change was assessed in three study areas that contained different mixes of grassland, pasture, and forest cover. Results showed that the deep-learning method produced the highest accuracy across all classes relative to an implementation of random forest that included some first-order texture measures. Overall accuracy was 4\% greater with the deep-learning classifier and class accuracies were more balanced. Evaluation of change accuracy suggested good performance for many conversions such as grassland to crop, forest to crop, water to dryland covers, and most bare/developed-related changes. Changes involving pasture with grassland or cropland were more difficult to detect due to spectral confusion among classes. Similarly, conversion to forests in some cases was poorly detected due to gradual and subtle change characteristics combined with confusion between forest, shrub, and croplands. The proposed framework involved several processing steps that can be explored to enhance the thematic content and accuracy for large regional implementation. Evaluation for understanding connectivity in natural land covers and related declines in species at risk is planned for future research.},
number = {4},
journal = {Remote Sensing},
author = {Pouliot, Darren and Alavi, Niloofar and Wilson, Scott and Duffe, Jason and Pasher, Jon and Davidson, Andrew and Daneshfar, Bahram and Lindsay, Emily},
month = feb,
year = {2021},
keywords = {NALCMS},
pages = {634},
}
Downloads: 0
{"_id":"3SiLZLT66DjqojbHf","bibbaseid":"pouliot-alavi-wilson-duffe-pasher-davidson-daneshfar-lindsay-assessmentoflandsatbaseddeeplearningmembershipanalysisfordevelopmentoffromtochangetimeseriesintheprairieregionofcanadafrom1984to2018-2021","author_short":["Pouliot, D.","Alavi, N.","Wilson, S.","Duffe, J.","Pasher, J.","Davidson, A.","Daneshfar, B.","Lindsay, E."],"bibdata":{"bibtype":"article","type":"article","title":"Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018","volume":"13","issn":"2072-4292","url":"https://www.mdpi.com/2072-4292/13/4/634","doi":"10.3390/rs13040634","abstract":"The prairie region of Canada is a dynamically changing landscape in relation to past and present anthropogenic activities and recent climate change. Improving our understanding of the rate, timing, and distribution of landscape change is needed to determine the impact on wildlife populations and biodiversity, ultimately leading to better-informed management regarding requirements for habitat amount and its connectedness. In this research, we assessed the viability of an approach to detect from–to class changes designed to be scalable to the prairie region with the capacity for local refinement. It employed a deep-learning convolutional neural network to model general land covers and examined class memberships to identify land-cover conversions. For this implementation, eight land-cover categories were derived from the Agriculture and Agri-Food Canada Annual Space-Based Crop Inventory. Change was assessed in three study areas that contained different mixes of grassland, pasture, and forest cover. Results showed that the deep-learning method produced the highest accuracy across all classes relative to an implementation of random forest that included some first-order texture measures. Overall accuracy was 4% greater with the deep-learning classifier and class accuracies were more balanced. Evaluation of change accuracy suggested good performance for many conversions such as grassland to crop, forest to crop, water to dryland covers, and most bare/developed-related changes. Changes involving pasture with grassland or cropland were more difficult to detect due to spectral confusion among classes. Similarly, conversion to forests in some cases was poorly detected due to gradual and subtle change characteristics combined with confusion between forest, shrub, and croplands. The proposed framework involved several processing steps that can be explored to enhance the thematic content and accuracy for large regional implementation. Evaluation for understanding connectivity in natural land covers and related declines in species at risk is planned for future research.","number":"4","journal":"Remote Sensing","author":[{"propositions":[],"lastnames":["Pouliot"],"firstnames":["Darren"],"suffixes":[]},{"propositions":[],"lastnames":["Alavi"],"firstnames":["Niloofar"],"suffixes":[]},{"propositions":[],"lastnames":["Wilson"],"firstnames":["Scott"],"suffixes":[]},{"propositions":[],"lastnames":["Duffe"],"firstnames":["Jason"],"suffixes":[]},{"propositions":[],"lastnames":["Pasher"],"firstnames":["Jon"],"suffixes":[]},{"propositions":[],"lastnames":["Davidson"],"firstnames":["Andrew"],"suffixes":[]},{"propositions":[],"lastnames":["Daneshfar"],"firstnames":["Bahram"],"suffixes":[]},{"propositions":[],"lastnames":["Lindsay"],"firstnames":["Emily"],"suffixes":[]}],"month":"February","year":"2021","keywords":"NALCMS","pages":"634","bibtex":"@article{pouliot_assessment_2021,\n\ttitle = {Assessment of {Landsat} {Based} {Deep}-{Learning} {Membership} {Analysis} for {Development} of from–to {Change} {Time} {Series} in the {Prairie} {Region} of {Canada} from 1984 to 2018},\n\tvolume = {13},\n\tissn = {2072-4292},\n\turl = {https://www.mdpi.com/2072-4292/13/4/634},\n\tdoi = {10.3390/rs13040634},\n\tabstract = {The prairie region of Canada is a dynamically changing landscape in relation to past and present anthropogenic activities and recent climate change. Improving our understanding of the rate, timing, and distribution of landscape change is needed to determine the impact on wildlife populations and biodiversity, ultimately leading to better-informed management regarding requirements for habitat amount and its connectedness. In this research, we assessed the viability of an approach to detect from–to class changes designed to be scalable to the prairie region with the capacity for local refinement. It employed a deep-learning convolutional neural network to model general land covers and examined class memberships to identify land-cover conversions. For this implementation, eight land-cover categories were derived from the Agriculture and Agri-Food Canada Annual Space-Based Crop Inventory. Change was assessed in three study areas that contained different mixes of grassland, pasture, and forest cover. Results showed that the deep-learning method produced the highest accuracy across all classes relative to an implementation of random forest that included some first-order texture measures. Overall accuracy was 4\\% greater with the deep-learning classifier and class accuracies were more balanced. Evaluation of change accuracy suggested good performance for many conversions such as grassland to crop, forest to crop, water to dryland covers, and most bare/developed-related changes. Changes involving pasture with grassland or cropland were more difficult to detect due to spectral confusion among classes. Similarly, conversion to forests in some cases was poorly detected due to gradual and subtle change characteristics combined with confusion between forest, shrub, and croplands. The proposed framework involved several processing steps that can be explored to enhance the thematic content and accuracy for large regional implementation. Evaluation for understanding connectivity in natural land covers and related declines in species at risk is planned for future research.},\n\tnumber = {4},\n\tjournal = {Remote Sensing},\n\tauthor = {Pouliot, Darren and Alavi, Niloofar and Wilson, Scott and Duffe, Jason and Pasher, Jon and Davidson, Andrew and Daneshfar, Bahram and Lindsay, Emily},\n\tmonth = feb,\n\tyear = {2021},\n\tkeywords = {NALCMS},\n\tpages = {634},\n}\n\n\n\n","author_short":["Pouliot, D.","Alavi, N.","Wilson, S.","Duffe, J.","Pasher, J.","Davidson, A.","Daneshfar, B.","Lindsay, E."],"key":"pouliot_assessment_2021","id":"pouliot_assessment_2021","bibbaseid":"pouliot-alavi-wilson-duffe-pasher-davidson-daneshfar-lindsay-assessmentoflandsatbaseddeeplearningmembershipanalysisfordevelopmentoffromtochangetimeseriesintheprairieregionofcanadafrom1984to2018-2021","role":"author","urls":{"Paper":"https://www.mdpi.com/2072-4292/13/4/634"},"keyword":["NALCMS"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/NAAtlas2024","dataSources":["yRJdyJoax6GFubwNS","WChDenW3ipDLTib3G","wszmZbW485BrvbZff","3fS6y29xitMxSyCmw","SmeabbQSEFozkXJuC","3cx6m8LrzQx6SsjF2","qLjf8q88GSLZ5dAmC"],"keywords":["nalcms"],"search_terms":["assessment","landsat","based","deep","learning","membership","analysis","development","change","time","series","prairie","region","canada","1984","2018","pouliot","alavi","wilson","duffe","pasher","davidson","daneshfar","lindsay"],"title":"Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018","year":2021}