Free satellite data key to conservation

Assessing representation of remote sensing derived forest structure and land cover across a network of protected areas

Protected areas (PA) are an effective means of conserving biodiversity and protecting suites of valuable ecosystem services. Currently, many nations and international governments use proportional area protected as a critical metric for assessing progress towards biodiversity conservation. However, the areal and other common metrics do not assess the effectiveness of PA networks, nor do they assess how representative PA are of the ecosystems they aim to protect. Topography, stand structure, and land cover are all key drivers of biodiversity within forest environments, and are well-suited as indicators to assess the representation of PA. Here, we examine the PA network in British Columbia, Canada, through drivers derived from freely-available data and remote sensing products across the provincial biogeoclimatic ecosystem classification system. We examine biases in the PA network by elevation, forest disturbances, and forest structural attributes, including height, cover, and biomass by comparing a random sample of protected and unprotected pixels. Results indicate that PA are commonly biased towards high-elevation and alpine land covers, and that forest structural attributes of the park network are often significantly different in protected versus unprotected areas (426 out of 496 forest structural attributes found to be different; p < 0.01). Analysis of forest structural attributes suggests that establishing additional PA could ensure representation of various forest structure regimes across British Columbia's ecosystems. We conclude that these approaches using free and open remote sensing data are highly transferable and can be accomplished using consistent datasets to assess PA representations globally.

Addressing the need for improved land cover map products for policy support

The continued increase of anthropogenic pressure on the Earth's ecosystems is degrading the natural environment and then decreasing the services it provides to humans. The type, quantity, and quality of many of those services are directly connected to land cover, yet competing demands for land continue to drive rapid land cover change, affecting ecosystem services. Accurate and updated land cover information is thus more important than ever, however, despite its importance, the needs of many users remain only partially attended. A key underlying reason for this is that user needs vary widely, since most current products - and there are many available - are produced for a specific type of end user, for example the climate modelling community. With this in mind we focus on the need for flexible, automated processing approaches that support on-demand, customized land cover products at various scales. Although land cover processing systems are gradually evolving in this direction there is much more to do and several important challenges must be addressed, including high quality reference data for training and validation and even better access to satellite data. Here, we 1) present a generic system architecture that we suggest land cover production systems evolve towards, 2) discuss the challenges involved, and 3) propose a step forward. Flexible systems that can generate on-demand products that match users' specific needs would fundamentally change the relationship between users and land cover products - requiring more government support to make these systems a reality.

Whale counting in satellite and aerial images with deep learning

Despite their interest and threat status, the number of whales in world’s oceans remains highly uncertain. Whales detection is normally carried out from costly sighting surveys, acoustic surveys or through high-resolution images. Since deep convolutional neural networks (CNNs) are achieving great performance in several computer vision tasks, here we propose a robust and generalizable CNN-based system for automatically detecting and counting whales in satellite and aerial images based on open data and tools. In particular, we designed a two-step whale counting approach, where the first CNN finds the input images with whale presence, and the second CNN locates and counts each whale in those images. A test of the system on Google Earth images in ten global whale-watching hotspots achieved a performance (F1-measure) of 81% in detecting and 94% in counting whales. Combining these two steps increased accuracy by 36% compared to a baseline detection model alone. Applying this cost-effective method worldwide could contribute to the assessment of whale populations to guide conservation actions. Free and global access to high-resolution imagery for conservation purposes would boost this process.