Mapping Large-Scale Forest Disturbance Types with Multi-Temporal CNN Framework

Forests play a vital role in combating gradual developmental deficiencies and balancing regional ecosystems, yet they are constantly disturbed by man-made or natural events. Therefore, developing a timely and accurate forest disturbance detection strategy is urgently needed. The accuracy of traditional detection algorithms depends on the selection of thresholds or the formulation of complete rules, which inevitably reduces the accuracy and automation level of detection. In this paper, we propose a new multitemporal convolutional network framework (MT-CNN). It is an integrated method that can realize long-term, large-scale forest interference detection and distinguish the types (forest fire and harvest/deforestation) of disturbances without human intervention. Firstly, it uses the sliding window technique to calculate an adaptive threshold to identify potential interference points, and then a multitemporal CNN network is designed to render the disturbance types with various disturbance duration periods. To illustrate the detection accuracy of MT-CNN, we conducted experiments in a large-scale forest area (about 990 km2) on the west coast of the United States (including northwest California and west Oregon) with long time-series Landsat data from 1986 to 2020. Based on the manually annotated labels, the evaluation results show that the overall accuracies of disturbance point detection and disturbance type recognition reach 90%. Also, this method is able to detect multiple disturbances that continuously occurred in the same pixel. Moreover, we found that forest disturbances that caused forest fire repeatedly appear without a significant coupling effect with annual temporal and precipitation variations. Potentially, our method is able to provide large-scale forest disturbance mapping with detailed disturbance information to support forest inventory management and sustainable development.

Smallholder agriculture results in stable forest cover in riverine Amazonia

Recent studies point to a rapid increase in small-scale deforestation in Amazonia. Where people live along the rivers of the basin, customary shifting cultivation creates a zone of secondary forest, orchards and crop fields around communities in what was once was old-growth terra firme forest. Visible from satellite imagery as a narrow but extensive band of forest disturbance along rivers, this zone is often considered as having been deforested. In this paper we assess forest disturbance and the dynamics of secondary forests around 275 communities along a 725 km transect on the Napo and Amazon rivers in the Peruvian Amazon. We used high-resolution satellite imagery to define the ‘working area’ around each community, based on the spatial distribution of forest/field patches and the visible boundary between old-growth and secondary forests. Land cover change was assessed between ca. 1989 and 2015 using CLASliteTM image classification. Statistical analyses using community and household-level data from the Peruvian Amazon Rural Livelihoods and Poverty (PARLAP) Project identified the predictors of the extent of forest disturbance and the dynamics of secondary forests around communities. Although shifting cultivation is the primary driver of old-growth forest loss, we find that secondary forest cover which replaces old-growth forests is stable through time, and that both the area and rate of expansion into old-growth forests are modest when compared to forest conversion in Peru for colonization and plantation development. Our findings challenge the notion that smallholder agriculture along rivers is an important threat to terra firme forests in Amazonia and point to the importance of protecting forests on community lands from loggers, colonists and other outsiders.