Welcome to Terra-i

Louis Reymondin

Welcome to our new website! In this portal to the Terra-i habitat change monitoring system, you will find a short description of our input and output data, you'll also be able to download the latest detections or view them with our web mapping tool. Don't miss our videos section where deforestation hot spots are presented, you'll also be able to request that we generate new video in areas of your interest. You can visualise habitat change directly but to access the data in GIS formats , you will need an account to our portal, if you don't have one, you can sign in by filling the registration form.

Terra-i: An eye on habitat change


Habitat conversion is contributing to widespread loss of biodiversity and other critical ecosystem services, yet in many parts of the world the scale and pattern of habitat loss goes unmonitored. Decision makers at multiple scales (local to national to regional) need timely information on land-cover change, requiring the information to be as accurate and recent as possible in order to prioritise interventions and act upon new land-cover change trends in a timely manner. The high temporal resolution (16 days) of MODIS NDVI data (product MOD13Q1) lends itself to being used to monitor land cover across large extents, but a combination of massive volumes of data and large amounts of noise in the time-series make this endeavour a challenge. We developed a methodology for detecting anthropogenic land-cover change across the tropics, which is capable of providing near real-time monitoring of habitat loss.
The methodology is based on the premise that natural vegetation follows a predictable pattern of changes in greenness from one date to the next that are brought about by site-specific characteristics and climatic conditions over the preceding days. We use a Bayesian-probability based neural network to learn how the greenness of a given pixel responds to a unit of rainfall (derived from the TRMM daily rainfall product 3b42), then we apply the model to identify anomalies in the time series - which can then be attributed to human activities (i.e. non-natural fluctuations in greenness). The methodology aims to demonstrate a potentially powerful means of monitoring habitat loss at a temporal and spatial resolution that is relevant for decision makers.

Important articles News category