Page tree

    Loading...


Lithology and Surficial Geology Mapping

Download Product Sheet


 

Lithological classification in the Shibanjing Ophiolite Complex in Inner Mongolia, China using Sentinel-2 and DEM using machine learning methods. (a) k-nearest neighbour (k-NN); (b) random forest classifier (RFC); (c) artificial neural network (ANN); (d) support vector machine (SVM); (e) maximum likelihood classification (MLC) (Source: Ge, W., Cheng, Q., Tang, Y., Jing, L. and Gao, C., 2018. Lithological classification using Sentinel-2A data in the Shibanjing ophiolite complex in Inner Mongolia, China. Remote Sensing, 10(4), p.638.).


Product Category

  • Land cover
  • Natural Disaster
  • Climate Change
  • Coast Management 
  • Marine
  • Earth's Surface Motion

Financial Domains

  • Risk Analysis 
  • Insurance management 
  • Green finance

User requirements 

UN9: Understanding stock levels and monitoring supply chains.

Description

This product provides a spatial characterization of surface rock and soil types based on satellite imagery. These maps can be used by mining exploration companies to know the mineral composition of the area they are exploring. Litho-types can be distinguished based on their spectral signatures, as well as their associations with topographical and geomorphological features, in particular surface texture (roughness) and patterns (including drainage patterns).

Spatial Coverage Target

Mining area

Data Throughput

Rapid tasking 

Data availability

  • High
  • High

PRODUCT SPECIFICATIONS

Main processing steps

Lithology and surficial geology maps are produced based on supervised classification techniques. These maps are produced by applying supervised classification algorithms (e.g., machine learning based algorithms) using data from multispectral imagery like Sentinel-2 and other ancillary EO data like DEM. These models should be trained by using reference maps which were generated by in-field surveys.

Input data sources

Optical:  Sentinel-2

Radar:  N.A

Supporting data:  DEM

Accessibility

Sentinel-2: is freely and publicly available through ESA.

Spatial resolution

Sentinel-2: 10 m

Frequency (Temporal resolution)

Sentinel-2: ~ 6 days

Latency

Sentinel-2: ≤ 1 day

Geographical scale coverage

Globally

Delivery/ output format

Data type: Raster

File format:  GeoTiff

Accuracies

Thematic accuracy: 75-85%

Spatial accuracy: 1.5-2 pixels of input data

Constraints and limitations

n Mapping lithology is most effective in arid and semi-arid regions.

n It becomes more difficult and less accurate in temperate and tropical areas where weathering is extensive, and dense vegetation cover is prevalent.

n Cloud presence.

n Rely on reference data.

User's level of knowledge and skills to extract information and perform further analysis on the EO products.

Skills: Essential

Knowledge: Essential

Similar Products

Planet Biomass Proxy (link)

Spatial resolution: 10 m

Frequency (Temporal resolution): Daily

Latency: 1 Day

Geographical scale coverage: Globally with gaps over some major agricultural areas of the world, due to the discontinuity of Sentinel-1B in December 2021

Delivery / output format: GeoTIFF, NetCDF (Raster), CSV (Time series)

Accuracies: 80-90%

Accessibility: Commercially available from Planet


 


Edit


P15: Lithology and surficial geology mapping

Download product sheet gap analysis

Maturity score

Mean: 3.00

STD: 0.00

Constraints and limitations

·  Cloud presence.

·  Mapping lithology is most effective in arid and semi-arid regions. It becomes more difficult and less accurate in temperate and tropical areas where weathering is extensive, and dense vegetation cover is prevalent.

·  The product relies on reference data.

·  Machine learning model uncertainty.

Relevant user needs

UN9: Understanding stock levels and monitoring supply chains.

R&D gaps

·  Limited training data.

·  Limited spectral bands of currently available EO data.

Potential improvements drivers

·  Using Hyperspectral data (there are upcoming missions).

·  More training datasets

Utilisation level review

Utilisation score

Mean: 2.00

STD: 0.00

No utilisation

Low utilisation

·  Unawareness of the existence of commercial EO products with better specifications

·  The product is already satisfying the technical and usability requirements.

Medium utilisation

High utilisation

Critical gaps related to relevant user needs

Utilisation gap

UN9: Understanding stock levels and monitoring supply chains

Edit
  • No labels

This page has no comments.