An eye on habitat change



Terra-i is a monitoring system for observing habitat changes in Latin America and the Caribbean. It uses neural networks and satellite data of vegetation index and precipitation to detect deviations from the normal pattern of the natural time cycle of vegetation and thus, potential anthropogenic impacts on natural ecosystems.

Terra-i is a collaboration between the International Center for Tropical Agriculture (CIAT – DAPA, based in Colombia), The program on Forestry, Trees and Agroforestry (FTA) ,The Nature Conservancy (TNC, global environmental organization), the School of Business and Engineering (HEIG-VD, based in Switzerland) and King’s College London (KCL, based in the UK). The system is based on the premise that natural vegetation follows a predictable pattern of changes in greenness from one date to the next brought about by site-specific land and climatic conditions over the same period. A so-called computational neural network is ‘trained’ to understand the normal pattern of changes in vegetation greenness in relation to terrain and rainfall for a site and then marks areas as changed where the greenness suddenly changes well beyond these normal limits. Running on many computers this analysis is refreshed with new imagery every 16 days and for every 250m square of land.



Main objective: use of high temporal frequency images (16 days) and moderate spatial resolution (250 m).

Terra-i Database:

In this database you will find data of changes in vegetation cover for areas in Latin America and the Caribbean since 2004 till date. The data are stored yearly every 16 days according to the Julian caldendar.


Download data



Database Structure:

The Terra-i database has 5 different tables:

  1. Area: contains information about the areas in Latin America and the Caribbean.
  1. Realtime: contains all data per year and within 16 days periods of changes in vegetation cover of all the available areas. These values are in hectares.
  1. Adminunit: contains the administrative units (department, district, province, country, region and state), and varies depending on the country.
  1. Type: contains the information that indicates the administrative level (country, department, protected area and ecosystem).
  1. Log: contains the information of consultations made about different areas; it is a basic form of managing the statistics of most consulted areas.