Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset

Understanding land cover holds considerable potential for a myriad of practical applications, particularly as data accessibility transitions from being exclusive to governmental and commercial entities to now including the broader research community. Nevertheless, although the data is accessible to...

Full description

Saved in:
Bibliographic Details
Main Authors: Victor Radermecker, Andrea Zanon, Nancy Thomas, Annita Vapsi, Saba Rahimi, Rama Ramakrishnan, Daniel Borrajo
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10887251/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715285578219520
author Victor Radermecker
Andrea Zanon
Nancy Thomas
Annita Vapsi
Saba Rahimi
Rama Ramakrishnan
Daniel Borrajo
author_facet Victor Radermecker
Andrea Zanon
Nancy Thomas
Annita Vapsi
Saba Rahimi
Rama Ramakrishnan
Daniel Borrajo
author_sort Victor Radermecker
collection DOAJ
description Understanding land cover holds considerable potential for a myriad of practical applications, particularly as data accessibility transitions from being exclusive to governmental and commercial entities to now including the broader research community. Nevertheless, although the data is accessible to any community member interested in exploration, there exists a formidable learning curve and no standardized process for accessing, preprocessing, and leveraging the data for subsequent tasks. In this study, we democratize this data by presenting a flexible and efficient end-to-end pipeline for working with the Dynamic World dataset, a cutting-edge near-real-time land use/land cover (LULC) dataset. This includes a preprocessing and representation framework which tackles noise removal, efficient extraction of large amounts of data, and re-representation of LULC data in a format well suited for several downstream tasks. To demonstrate the power of our pipeline, we use it to extract data for an urbanization prediction problem and build a suite of machine learning models with excellent performance. This task is easily generalizable to the prediction of any type of land cover and our pipeline is also compatible with a series of other downstream tasks. To facilitate further research and validation, all code and data used in this study are made available online.
format Article
id doaj-art-ea7e56b4a49e4ccda795780f6e3d325e
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-ea7e56b4a49e4ccda795780f6e3d325e2025-08-20T03:13:26ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01186440645010.1109/JSTARS.2025.354228210887251Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World DatasetVictor Radermecker0https://orcid.org/0009-0007-8418-8993Andrea Zanon1https://orcid.org/0009-0002-8918-8419Nancy Thomas2https://orcid.org/0009-0008-5333-7746Annita Vapsi3https://orcid.org/0009-0000-7751-5254Saba Rahimi4Rama Ramakrishnan5https://orcid.org/0009-0008-9575-3457Daniel Borrajo6https://orcid.org/0000-0001-5282-0463MIT Sloan School of Management and Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USAMIT Sloan School of Management and Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USAJP Morgan, New York, NY, USAJP Morgan, New York, NY, USAJP Morgan, New York, NY, USAMIT Sloan School of Management and Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, USAJP Morgan, New York, NY, USAUnderstanding land cover holds considerable potential for a myriad of practical applications, particularly as data accessibility transitions from being exclusive to governmental and commercial entities to now including the broader research community. Nevertheless, although the data is accessible to any community member interested in exploration, there exists a formidable learning curve and no standardized process for accessing, preprocessing, and leveraging the data for subsequent tasks. In this study, we democratize this data by presenting a flexible and efficient end-to-end pipeline for working with the Dynamic World dataset, a cutting-edge near-real-time land use/land cover (LULC) dataset. This includes a preprocessing and representation framework which tackles noise removal, efficient extraction of large amounts of data, and re-representation of LULC data in a format well suited for several downstream tasks. To demonstrate the power of our pipeline, we use it to extract data for an urbanization prediction problem and build a suite of machine learning models with excellent performance. This task is easily generalizable to the prediction of any type of land cover and our pipeline is also compatible with a series of other downstream tasks. To facilitate further research and validation, all code and data used in this study are made available online.https://ieeexplore.ieee.org/document/10887251/Convolutional long short-term memory (ConvLSTM)deep neural networksdynamic world (DW) datasetland use and land cover (LULC)machine learningremote sensing
spellingShingle Victor Radermecker
Andrea Zanon
Nancy Thomas
Annita Vapsi
Saba Rahimi
Rama Ramakrishnan
Daniel Borrajo
Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Convolutional long short-term memory (ConvLSTM)
deep neural networks
dynamic world (DW) dataset
land use and land cover (LULC)
machine learning
remote sensing
title Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
title_full Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
title_fullStr Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
title_full_unstemmed Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
title_short Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset
title_sort enabling advanced land cover analytics an integrated data extraction pipeline for predictive modeling with the dynamic world dataset
topic Convolutional long short-term memory (ConvLSTM)
deep neural networks
dynamic world (DW) dataset
land use and land cover (LULC)
machine learning
remote sensing
url https://ieeexplore.ieee.org/document/10887251/
work_keys_str_mv AT victorradermecker enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT andreazanon enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT nancythomas enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT annitavapsi enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT sabarahimi enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT ramaramakrishnan enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset
AT danielborrajo enablingadvancedlandcoveranalyticsanintegrateddataextractionpipelineforpredictivemodelingwiththedynamicworlddataset