University Research Council

Features

...
Facial Recognition Technology, for Fish.

Traditional methods of gathering fisheries data can take as long as one or two years, costing time and money that many imperiled global fisheries don’t have. Enter FishFace, a new application under development by The Nature Conservancy in partnership with Refind Technologies. Similar to facial recognition software used to identify people, FishFace uses artificial intelligence to learn to recognize fish species in photographs. “When it comes to fisheries management,” Dr. Chris Gillies of The Nature Conservancy in Australia explains, “what sets apart the stocks that aren’t overfished is good data about the size and distribution of those fish.” FishFace will make fisheries data available in real time. The project is a finalist in the 2016 Google Impact Challenge: Australia with the potential to receive $750,000 in funding to trial FishFace in Indonesia’s snapper and grouper fisheries.
...
Bioacoustics Reveal How Biodiversity Changes Across Borneo’s Logged Forests

The chainsaw roars to life and the stench of gasoline fills the air. Steel meets hardwood, and dust pulses from the wound like arterial spray, raining down onto the clay soil as the blade cuts deeper into the massive dipterocarp. Then the tree groans. It falls — seemingly in slow motion as wood splinters and earth rips — tearing down vines and obliterating smaller trees beneath its bulk. And then comes the silence, punctuated by the dying sputters of the chainsaw. I’m deep in a logging concession in Indonesian Borneo, and I’ve just witnessed the routine harvesting of a dipterocarp tree bound for the plywood mill. Vast stands of selectively logged forest still remain, but many parts of Indonesia are transitioning from forestry to more intensive land uses, like oil palm and acacia plantations. And with those changes come impacts to the region’s biodiversity and ecosystem services.
...
Precision Agriculture: Potential and Limits

Digital technology applied to farm machinery and cloud-based information is making farming seem like science fiction in some places. Drones buzz over the landscape monitoring crop conditions and spotting problems, like pest infestations or weeds. Farmers receive personalized weather information which predicts how rainfall will vary from one field to the next. Soils are mapped at a level of precision unimaginable only a few years ago, and sensors tell farmers exactly how much water is being used at thousands of different data points. The cabins of farm machinery are filled with GPS systems and drivers no longer drive. Instead, they sit in the cabin checking screens that control the appliances, which move across fields delivering precisely measured quantities of inputs in precisely the best place, at programmed times, in perfectly straight lines or contoured to the land—whatever the data determines will give the best yield.
...
Solar Energy Development Doesn’t Have to Destroy Vital Habitat (but It Could)

“There are some caveats here,” said lead author Michael Levin, “and it’s important to note that there is substantial variation in how much land is likely to be converted at state levels. Some states are projected to see really high levels of development occurring on land with high value for animal movement.” Scientists note that though solar development is not projected to be a massive driver of land-cover change relative to other drivers, such as agriculture or urbanization, some land covers with higher value for animal movement (deciduous forest in particular) are projected to be converted to solar energy more than other land covers with lower value for animal movement, such as barren lands or intensive agricultural landscapes.