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...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |