A major recent trend in remote sensing research is the analysis of satellite image time series for land use and land cover monitoring and mapping. In this paper, we describe the Time-Weighted Dynamic Time Warping algorithm, which improves on previously proposed methods for land cover and land use classification. The method is based on the dynamic time warping method that measures similarity between two temporal sequences. We modified this method to account for seasonality of land cover types. The resulting algorithm is flexible to account for different cropland systems, tropical forests, and pasture using few training samples. The algorithm had better results than other Dynamic Time Warping variations for land classification. The method is suitable to make land use and land cover maps and has potential for large-scale analysis at country or continental scale, using global data sets such as the EVI time series from the MODIS sensor.

Mapping forest types and tree species at regional scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. Here, we assess the potential of a U‐net convolutional network, a recent deep learning algorithm, to identify and segment (1) natural forests and eucalyptus plantations, and (2) an indicator of forest disturbance, the tree species Cecropia hololeuca, in very high resolution images (0.3 m) from the WorldView‐3 satellite in the Brazilian Atlantic rainforest region. The networks for forest types and Cecropia trees were trained with 7611 and 1568 red‐green‐blue (RGB) images, respectively, and their dense labeled masks. Eighty per cent of the images were used for training and 20% for validation. The U‐net network segmented forest types with an overall accuracy >95% and an intersection over union (IoU) of 0.96. For C. hololeuca, the overall accuracy was 97% and the IoU was 0.86. The predictions were produced over a 1600 km2 region using WorldView‐3 RGB bands pan‐sharpened at 0.3 m. Natural and eucalyptus forests compose 79 and 21% of the region's total forest cover (82 250 ha). Cecropia crowns covered 1% of the natural forest canopy. An index to describe the level of disturbance of the natural forest fragments based on the spatial distribution of Cecropia trees was developed. Our work demonstrates how a deep learning algorithm can support applications such as vegetation, tree species distributions and disturbance mapping on a regional scale.

Our limited understanding of the climate controls on tropical forest seasonality is one of the biggest sources of uncertainty in modeling climate change impacts on terrestrial ecosystems. Combining leaf production, litterfall and climate observations from satellite and ground data in the Amazon forest, we show that seasonal variation in leaf production is largely triggered by climate signals, specifically, insolation increase (70.4% of the total area) and precipitation increase (29.6%). Increase of insolation drives leaf growth in the absence of water limitation. For these non-water-limited forests, the simultaneous leaf flush occurs in a sufficient proportion of the trees to be observed from space. While tropical cycles are generally defined in terms of dry or wet season, we show that for a large part of Amazonia the increase in insolation triggers the visible progress of leaf growth, just like during spring in temperate forests. The dependence of leaf growth initiation on climate seasonality may result in a higher sensitivity of these ecosystems to changes in climate than previously thought.

No abstract

Many elements determine land sensitivity to desertification, whose analysis requires multifactorial approaches to be used. The environmental sensitive areas methodology is a well-known approach to estimate sensitivity to desertification that accounts for multiple interacting driving forces, conceived and validated in a Mediterranean environment. We show that the environmental sensitive areas methodology can be used, with minor modifications, in a tropical context, where it allows the discrimination among environments with different degree of susceptibility to degradation and resilience. The results obtained for the Dominican Republic show that 48·4% of its territory is critically sensitive to desertification, and 16·4% of it is highly critically sensitive to desertification, mostly because of intense and inadequate land use practices.