Terra-i is a near-real time monitoring system for natural vegetation conversion at pan-tropical scale which is now being scaled for application across the entire tropics. It uses satellite data and computational neural networks to detect anthropogenic changes in the vegetation cover every 16 days.
Terra-i uses computational neural networks to detect or ‘learn’ how the vegetation vigor behaves at each site over a period in relation to observed rainfall. This knowledge of historic vegetation response to rainfall is then applied to current measurements of rainfall to predict what the vegetation response should be. This prediction is then compared with Normalized Difference Vegetation Index (NDVI) data taken by the satellite and if the observed response is significantly different from the historic responses given the pattern of rainfall, then the pixel is marked as one that may have changed through anthropogenic means. If this change remains two 16-day periods in a row, then the event is confirmed. Much work is carried out to account for and remove the effects of drought, flooding and cloud cover or other image ‘noise’ that may produce false positives.
In what context is this tool useful?
Terra-i tool is useful in a context where stakeholders need to identify land-cover changes resulting from human activities and make use of data at different levels. Stakeholders can use this information to carry out natural resource management actions and create synergies between national and local institutions for protection and conservation, as well as improve the governance processes of natural resources at the local, municipal, and national levels.
The tool has been adopted and implemented with the experience, local knowledge, and support of the national and sub-national governments of Peru, Colombia (Valle del Cauca), Honduras and Vietnam.
Also, the tool was implemented in a road impact assessment in five case studies in Latin America.
Since June 2012, Terra-i has data available for free download at www.terra-i.org. There has been a vegetation loss map produced every 16 days from January 2004 to the current date, at the pantropical level.
Louis Reymondin - L.Reymondin@cgiar.org