planetscope
There are 1 repository under planetscope topic.
- eoreader
sertit / eoreader
Remote-sensing opensource python library reading optical and SAR sensors, loading and stacking bands, clouds, DEM and spectral indices in a sensor-agnostic way.
Language:Python 266 j-desloires / eo-crops
A collection of python code to download and preprocess satellite images for crop monitoring at field-level
Language:Python 8torhaa1 / Planetscope_preprocessing
Notebooks for preprocessing and analysis of Planetscope 4 band data/imagery, using rasterio and fiona.
Language:Jupyter Notebook 7GISLab-ELTE / WasteDetection
Waste Detection and Change Analysis based on Multispectral Satellite Imagery
Language:Python 5LLeiSong / hrlcm
Land cover classification in Tanzania using ensemble labels and high resolution Planet NICFI basemaps and Sentinel-1 time series.
Language:Python 4j0nflores / planet-hma-streams
This repo contains implementations of water classification methods to detect small proglacial streams in High Mountain Asia (HMA) using high-resolution PlanetScope imagery.
Language:Python 3ValentinSchmittDeer / dsm-from-planetscope
Master thesis in 2021 with University of Stuttgart and Planet Labs
Language:Python 3inrea21 / Colombia-Analysis
As the population increases, demand for food increases too, which has led to large-scale land conversion to improve livestock production in Colombia. Fulfilling these criteria of increasing demand in a sustainable way is a challenge and remote sensing data provides an accurate method to support this task. In this study, Planet Scope multispectral satellite datasets and coincident field measurements acquired over test fields in the study area (Patía) of September 2018 was be used. Fresh and dry weight biomass was calculated and forage quality analyses, crude protein (CP), in vitro dry matter digestibility (IVDMD), Ash and standing biomass dry weight (DM) was carried out in the forage nutritional quality laboratory of International Centre for Tropical Agriculture (CIAT). Field data was related to the remote sensing data using the random forest regression algorithm. R was required for the statistical analysis, to figure out the model performance for IVDMD, CP, Ash and DM. This project also investigated the spatial distribution of livestock which is affected by quality and area of potential forage zones. The R2 values of the regression models were 0.74 for IVDMD, 0.69 for CP, 0.38 for Ash and 0.49 for DM using a predictor combination of vegetation indices, simple ratios and bands.
Language:R 1n-verde / Indicator_11.7.1
mapping urban open spaces and land allocated to streets, using remote sensing, for aiding the calculation of SDG indicator 11.7.1.
Language:Jupyter Notebook 1sparkgeo / world_bank_deliverable
Directory to hold the deliverables for the World Bank project.
Language:Jupyter Notebook 1- Language:R 0
