Land Subsidence Data
Buy and sell land subsidence data data. InSAR-derived ground movement measurements showing sinking areas. Infrastructure risk AI identifies subsidence zones before damage occurs.
No listings currently in the marketplace for Land Subsidence Data.
Find Me This Data →Overview
What Is Land Subsidence Data?
Land subsidence data represents ground movement measurements derived from InSAR (Interferometric Synthetic Aperture Radar) technology, which detects when land surface elevation lowers over time. This geohazard occurs from both natural processes—such as sediment compaction and tectonic activity—and human activities including groundwater extraction, mining, and industrial development. InSAR-derived datasets provide wide-area velocity fields at approximately 100-meter resolution, enabling consistent monitoring across large geographic regions. Subsidence prediction and early monitoring are critical for infrastructure protection and urban planning. Machine learning models applied to InSAR time-series data can estimate subsidence susceptibility, helping policymakers integrate land stability considerations into development decisions. Cities like Mexico City have experienced subsidence rates exceeding 30 cm per year, while Greater Houston recorded over 5 cm annually, demonstrating the severity and geographic diversity of this hazard.
Market Data
38 mm/year
Palembang subsidence rate
Source: ScienceDirect
30+ cm/year
Mexico City maximum subsidence
Source: ScienceDirect
5+ cm/year
Greater Houston subsidence range
Source: ScienceDirect
~100 meters
InSAR mapping resolution
Source: ScienceDirect
2,251 images
Sentinel-1 images used (NCP study)
Source: ScienceDirect
Who Uses This Data
What AI models do with it.do with it.
Urban Planning & Infrastructure Risk
Municipalities and developers use subsidence maps to guide infrastructure construction and ensure new development accounts for land stability. Proactive prediction helps safeguard human and environmental safety by integrating subsidence risk into zoning and building code decisions.
Water Resource Management
Water authorities employ subsidence data to monitor impacts of groundwater extraction and validate effectiveness of sustainable management policies. Time-series analysis tracks subsidence patterns before and after regulatory interventions like extraction bans and water resource fees.
Mining & Industrial Monitoring
Mining operations and industrial facilities use subsidence predictions to assess ground collapse risks from excavation, tunneling, and fluid withdrawal. Machine learning models forecast mining-induced subsidence to prevent sudden or progressive ground failure.
Agricultural & Irrigation Planning
Agricultural regions monitor subsidence linked to irrigation practices and aquifer recharge rates. Data supports decisions on irrigation methods and water extraction policies to reduce subsidence vulnerability in high-water-demand areas.
What Can You Earn?
What it's worth.worth.
Regional InSAR datasets
Varies
Price depends on geographic coverage, temporal resolution, and number of SAR frames processed
City-scale subsidence maps
Varies
Varies based on map resolution, area size, and validation against ground stations
ML-enhanced predictions
Varies
Premium pricing for machine learning model outputs and susceptibility forecasts
Historical time-series
Varies
Multi-year subsidence records with hydrological correlation command higher rates
What Buyers Expect
What makes it valuable.valuable.
Temporal consistency across SAR frames
Data must account for horizontal motion of tectonic plates and overlap regions between consecutive tracks to reduce dispersion and ensure consistent velocity fields across wide-area scenes.
Ground validation and CORS integration
Datasets should be validated against CORS (Continuously Operating Reference Stations) ground measurements. Studies employ 70/30 train-test splits to demonstrate reliability and generalizability of predictions.
Fine spatial resolution
Buyers expect approximately 100-meter resolution or better to enable infrastructure-level risk assessment and urban planning decisions at meaningful geographic scales.
Multi-source environmental correlation
Quality datasets incorporate hydrological data, precipitation records, soil water layers, and aquifer characteristics to improve prediction accuracy beyond time-series subsidence alone.
Computational efficiency documentation
Providers should document computational efficiency and uncertainty quantification, particularly when processing large-scale scenarios with millions of SAR candidates.
Companies Active Here
Who's buying.buying.
Integration of subsidence risk into urban development strategies, zoning decisions, and infrastructure construction to ensure land stability and human safety
Monitoring groundwater extraction impacts, validating policy effectiveness, and implementing sustainable water management practices to balance resource extraction with land stability
Predicting mining-induced subsidence and ground collapse risks from excavation, tunneling, and fluid withdrawal to prevent infrastructure failure
Assessing subsidence risks in irrigation-intensive regions and optimizing water extraction policies based on aquifer characteristics and recharge rates
FAQ
Common questions.questions.
What technology produces land subsidence data?
InSAR (Interferometric Synthetic Aperture Radar) is the primary technology, using remote sensing instruments like Sentinel-1 SAR to measure ground deformation over wide areas. Machine learning models are then applied to time-series InSAR data to predict subsidence susceptibility and generate risk maps.
How accurate is InSAR-derived subsidence mapping?
Modern InSAR approaches achieve approximately 100-meter spatial resolution and are validated against ground-based CORS stations. Studies demonstrate reliability through 70/30 train-test validation splits, though accuracy varies based on terrain, atmospheric conditions, and the number of SAR images processed.
Which regions show the highest subsidence risk?
Urban areas with intensive groundwater extraction face greatest vulnerability. Mexico City has experienced subsidence exceeding 30 cm per year, Greater Houston over 5 cm annually, and Palembang 38 mm per year. The North China Plain, San Joaquin Valley California, Bangkok, and other aquifer-stressed regions show high subsidence rates.
Can subsidence be predicted before it causes damage?
Yes. Machine learning models integrated with hydrological data can estimate subsidence likelihood in areas experiencing groundwater extraction. Effective prediction enables proactive mitigation through sustainable water management, adjusted building codes, and infrastructure planning that accounts for land stability risks.
Sell yourland subsidencedata.
If your company generates land subsidence data, AI companies are actively looking for it. We handle pricing, compliance, and buyer matching.
Request Valuation