Appendix A — Glossary of Key Terms
Agricultural Geospatial Intelligence
The use of satellite imagery, weather data, land-use information, and spatial analytics to understand agricultural conditions, crop performance, and environmental risks across large geographic areas.
Agricultural geospatial intelligence provides governments and agronomists with a consistent, objective view of agricultural landscapes.
Agroecological Zone
A geographic area defined by similar climate, soil conditions, terrain, and agricultural potential.
Agroecological zones are often used to guide crop suitability analysis, agricultural planning, and policy decisions.
Analysis-Ready Data (ARD)
Satellite or geospatial data that has already been processed to remove errors and standardize measurements so it can be analyzed immediately without additional preparation.
Typical processing steps include cloud removal, atmospheric correction, and geospatial alignment.
Band (Spectral Band)
A specific wavelength range of light measured by satellite sensors.
Different spectral bands reveal different characteristics of the Earth’s surface, such as vegetation health, soil exposure, or water presence.
Crop Classification
A machine-learning process that identifies the likely crop type growing in a location based on patterns observed in satellite imagery over time.
Models analyze vegetation growth patterns, spectral signatures, and seasonal cycles to estimate which crops are present.
Crop Condition Monitoring
The practice of using vegetation indicators and time-series satellite data to track crop growth, plant vigor, and signs of stress throughout the growing season.
This monitoring helps detect potential production risks early.
Crop Phenology
The study of seasonal crop development stages such as planting, emergence, flowering, and harvest.
Satellite time-series observations can help identify phenological patterns and detect abnormal crop development.
Drought Index
A numerical indicator used to measure the severity of drought conditions.
Common drought indices include rainfall anomalies and the Standard Precipitation Index (SPI), which compares current rainfall levels to historical averages.
Early Warning System
A monitoring system designed to detect emerging risks early enough to allow preventive action.
In agriculture, early warning systems combine satellite data, weather observations, and crop monitoring to identify potential food-security risks before harvest.
Flood Risk Modeling
The analysis of terrain, rainfall patterns, drainage networks, and water accumulation zones to identify areas that may experience flooding.
Flood risk modeling helps detect regions where excess water could damage crops or disrupt agricultural production.
Geospatial Data
Any data associated with a specific geographic location.
Examples include satellite imagery, weather measurements tied to coordinates, field boundaries, and administrative regions.
Geospatial data enables analysis of spatial patterns across landscapes.
Hydrology
The study of water movement across the landscape, including rainfall, runoff, river flow, and water accumulation.
Hydrology data helps identify flood risk and water availability for agriculture.
Land Use Mapping
The process of identifying how land is being used across a landscape, such as agriculture, forest, water bodies, or settlements.
Satellite imagery and spatial analysis are commonly used to generate land-use maps.
Machine Learning (ML)
A type of artificial intelligence that allows computer models to identify patterns in data and improve predictions over time.
In agricultural geospatial systems, machine learning is commonly used for crop classification, anomaly detection, and production forecasting.
NDVI (Normalized Difference Vegetation Index)
A widely used vegetation index derived from satellite imagery that measures plant health and biomass.
Higher NDVI values generally indicate healthy, actively growing vegetation, while lower values may indicate stressed crops or bare soil.
Pixel (Spatial Resolution)
The smallest unit of a satellite image.
Each pixel represents a square area on the ground. For example, Sentinel-2 imagery typically represents areas approximately 10 meters by 10 meters per pixel.
Remote Sensing
The process of collecting information about the Earth’s surface using satellites, aircraft, or drones without direct contact with the ground.
Remote sensing enables large-scale monitoring of vegetation, water, soil conditions, and land use.
Sentinel-2
A European Earth observation satellite system operated by the European Space Agency.
Sentinel-2 provides high-resolution multispectral imagery with frequent revisit times, making it well suited for monitoring vegetation, crops, and land use.
Spatial Aggregation
The process of summarizing detailed geographic data (such as pixel-level observations) into larger geographic units such as districts, municipalities, or agricultural zones.
Aggregation helps convert detailed geospatial observations into information useful for policy and planning.
Spatial Indexing
A method used in geospatial databases to organize location-based data so it can be retrieved efficiently.
Spatial indexing allows systems to quickly identify all data points within a particular geographic region.
Time-Series Analysis
The analysis of data collected repeatedly over time.
In agricultural monitoring, time-series analysis helps track crop development, detect abnormal growth patterns, and compare current seasons with historical trends.
Vegetation Index
A numerical indicator calculated from combinations of satellite spectral bands to estimate vegetation health.
Vegetation indices help detect plant vigor, biomass, and stress conditions.
Common examples include:
- NDVI (Normalized Difference Vegetation Index)
- EVI (Enhanced Vegetation Index)
- NDWI (Normalized Difference Water Index)
Weather Interpolation
A statistical technique used to estimate weather conditions in locations where direct measurements are unavailable.
By analyzing surrounding weather stations and spatial patterns, interpolation creates continuous weather datasets across large regions.
Yield Forecasting
The process of estimating expected crop production before harvest.
Yield forecasting typically combines information about planted crop area, vegetation health indicators, historical yield patterns, and weather conditions.