skills.rest
xjtulyc
xjtulycCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agri-remote-sensing

Extract cloud-masked NDVI/EVI/LSWI time series and phenological metrics from Sentinel-2 imagery.

33|6|Updated Mar 17, 2026
Search Tags:#agriculture#yield prediction#remote sensing#random forest#sentinel-2#ndvi phenology#google earth engine
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill agri-remote-sensing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agri-remote-sensing
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/19-agriculture/agri-remote-sensing
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill agri-remote-sensing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you convert agricultural satellite observations into actionable crop intelligence by building NDVI phenology time series, estimating biophysical indicators, and predicting yield.

Core Features & Use Cases

  • Cloud-free Sentinel-2 vegetation index time series: Build biweekly median NDVI/EVI/LSWI composites from Google Earth Engine and extract region-level time series.
  • Phenology extraction: Compute start/end of season, peak NDVI, and length of season from threshold-based NDVI dynamics.
  • Decision-support outputs: Estimate LAI from NDVI using empirical models and support crop type mapping and yield prediction using machine learning/regression.
  • Use Case: Analyze a growing season (e.g., a corn belt) to derive SOS/EOS/peak metrics, estimate LAI, classify crop types, and train a yield model using phenology features.

Quick Start

Use the skill to generate a biweekly Sentinel-2 NDVI time series for your ROI, extract SOS/EOS/peak phenology metrics, estimate LAI, and run yield prediction from the derived features.

Frequently Asked Questions about agri-remote-sensing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate NDVI time series from Sentinel-2 for crop yield prediction?▼

You can extract NDVI phenology metrics by computing threshold-based start of season (SOS), end of season (EOS), peak NDVI, and length of season from the generated biweekly Sentinel-2 vegetation index time series.

Can I estimate LAI from Sentinel-2 NDVI using Google Earth Engine?▼

This Skill supports crop type classification by using the derived NDVI phenology metrics and vegetation index time series as inputs for downstream machine learning models, specifically mentioning random forest for agricultural mapping workflows.

What is the best way to compute phenology metrics like SOS and EOS from satellite imagery?▼

Before using this Skill, you must initialize Google Earth Engine and define your region of interest, as the workflow requires Sentinel-2 L2A ingestion and region-wise vegetation index statistics extraction to function properly.

Does this Skill support random forest for crop type classification and yield prediction?▼

Yes, this Skill supports random forest and regression models for crop type classification and yield prediction, utilizing the derived phenology features and vegetation indices as training inputs.

Related Skills

Explore More Education & Research Skills→
xjtulycxjtulyc
33

satellite-imagery

Compute vegetation indices, LULC classifications, and bitemporal change products from satellite imagery via Google Earth Engine.

Community
Intermediate
huggingfacehuggingface
10.9k

hugging-face-evaluation

Convert README evaluation tables into Hugging Face model-index format.

Official
Advanced
HomericIntelligenceHomericIntelligence
18

evaluate-model

Evaluate machine learning model performance on test datasets using specified metrics.

Official
Intermediate
brainbytes-devbrainbytes-dev
10

alternative-data

Integrate alternative data sources to generate trading signals for equities and macro assets.

Community
Advanced