B5. Resilience, Third Nature, and Transition

• At 18 cents a gallon, suspending the federal gas tax would only save drivers a few pennies on pump prices that have topped $4.50, on average (Wall Street Journal; paywall). Gas stations often pocket the difference, and encouraging people to drive more during a shortage could push prices even higher (CNN). It would also drain the already insufficient highway trust fund (PBS). Even if state gas taxes were suspended, too, gas would still be 35 percent higher than before the war on Iran (NBC News).
• Transportation Secretary Sean Duffy continues to get dunked on for filming a reality TV show funded by companies his department regulates. (NPR)
• Too many transit projects get bogged down because an agency tries to engineer its way around a problem rather than try to work things out with other agencies involved. (Infrastory)
• Electrifying bus fleets involves a lot more than just acquiring the buses. (Metro Magazine)
• Waymo and Waze recently started sharing pothole data with cities, and now a company that sells security cameras for trucks is offering the same service. (TechCrunch)
• After the H Street streetcar was unceremoniously shut down, the D.C. Metro is now considering a bus rapid transit line along H Street to get Commanders fans to the new RFK Stadium because a rail station won’t be open by 2030. (WUSA)
• The board of Vancouver, Washington transit agency C-Tran voted to support light rail along the controversial I-5 bridge connecting the city to Portland. (The Columbian)
• The Charlotte city council reversed course on supporting new toll lanes on I-77. (Observer)
• An Atlanta city council member pulled a bill to separate “heels” and “wheels” on the Atlanta Beltline, which transit advocates said would preclude future rail, but supporters said would protect pedestrians from the scourge of e-scooters. (AJC)
• New Jersey Gov. Mikie Sherrill announced a plan to improve cleanliness, reliability, access and safety for NJ Transit. (NJ Business Magazine)
• Is Florida private passenger rail company Brightline headed for bankruptcy? (Palm Beach Post; paywall)
• A Kansas City program is helping small businesses find empty storefronts along the streetcar line. (KSHB)
• Unfortunately, America’s fondness for oversized SUVs is spreading to Europe. (The Guardian)
• A new report established a baseline for English roads’ carbon footprint to help reduce emissions in the future. (Smart Cities World)

Scientists, including ecologists, are data hogs. More data can give analyses more statistical power, increasing confidence that a researcher is seeing something real in the numbers, whether it’s fluctuations in an animal’s numbers, location, or some other metric. There is generally no such thing as “too much data.”

Except when there is. As technological advances enable people to collect more information, such as images from satellites or audio from tiny weather-resistant recorders, some scientists are drowning in data.

Just one example: The proliferation of small, cheap wildlife cameras has enabled researchers to amass tens of thousands of images that can take months of tedious work to catalog. Recently, AI tools have been some help, enabling scientists to, for example, sift out images containing no wildlife at all. But people are often still spending months scrolling through grainy snapshots before doing any of the “real” analysis. In computer parlance, there’s still a “human in the loop.”

That might not be true soon, however. AI-powered programs have grown sophisticated enough that in some cases they can screen and analyze wildlife camera data with enough accuracy that the final result isn’t meaningfully different from the more common labor-intensive approach, according to a new paper in the Journal of Applied Technology. In other words, no more human in the loop.

“We’re not trying to replace people,” said Washington State University wildlife ecologist Daniel Thornton, the study’s lead author. “The goal is to help researchers get to answers faster so they can make better decisions about managing and conserving wildlife.”

The new research didn’t involve some fancy technical breakthrough in AI programming. Rather, ecologists like Thornton collaborated with people at tech giant Google to see how they could harness existing AI tools. To do that, they set up what amounted to a competition: computers versus humans.

They started with nearly 3.8 million digital photos taken by 1,200 wildlife cameras in three different locations – eastern and central Washington state, Glacier National Park in Montana, and a jungle reserve in Guatemala. The photos had been scrutinized by experts to identify the species of any mammal that turned up. Then the researchers handed them over to AI.

 

.IRPP_ruby , .IRPP_ruby .postImageUrl , .IRPP_ruby .centered-text-area {height: auto;position: relative;}.IRPP_ruby , .IRPP_ruby:hover , .IRPP_ruby:visited , .IRPP_ruby:active {border:0!important;}.IRPP_ruby .clearfix:after {content: "";display: table;clear: both;}.IRPP_ruby {display: block;transition: background-color 250ms;webkit-transition: background-color 250ms;width: 100%;opacity: 1;transition: opacity 250ms;webkit-transition: opacity 250ms;background-color: #eaeaea;}.IRPP_ruby:active , .IRPP_ruby:hover {opacity: 1;transition: opacity 250ms;webkit-transition: opacity 250ms;background-color: inherit;}.IRPP_ruby .postImageUrl {background-position: center;background-size: cover;float: left;margin: 0;padding: 0;width: 31.59%;position: absolute;top: 0;bottom: 0;}.IRPP_ruby .centered-text-area {float: right;width: 65.65%;padding:0;margin:0;}.IRPP_ruby .centered-text {display: table;height: 130px;left: 0;top: 0;padding:0;margin:0;padding-top: 20px;padding-bottom: 20px;}.IRPP_ruby .IRPP_ruby-content {display: table-cell;margin: 0;padding: 0 74px 0 0px;position: relative;vertical-align: middle;width: 100%;}.IRPP_ruby .ctaText {border-bottom: 0 solid #fff;color: #0099cc;font-size: 14px;font-weight: bold;letter-spacing: normal;margin: 0;padding: 0;font-family:'Arial';}.IRPP_ruby .postTitle {color: #000000;font-size: 16px;font-weight: 600;letter-spacing: normal;margin: 0;padding: 0;font-family:'Arial';}.IRPP_ruby .ctaButton {background: url(https://www.anthropocenemagazine.org/wp-content/plugins/intelly-related-posts-pro/assets/images/next-arrow.png)no-repeat;background-color: #afb4b6;background-position: center;display: inline-block;height: 100%;width: 54px;margin-left: 10px;position: absolute;bottom:0;right: 0;top: 0;}.IRPP_ruby:after {content: "";display: block;clear: both;}Recommended Reading:Cloudy with a chance of warblers

 

First, they used MegaDetector, a program that detects whether animals, humans or vehicles are in an image. After that initial screening, the animal-positive images were turned over to SpeciesNet, a Google-developed program built to identify what animals are in a photo. It covers approximately 2,500 different groups of species from around the world. The results were then fed into a computer model built to convert these animal sightings into an estimation of where each species occurred on a landscape, what’s known as “occupancy.”

With the exception of a few outliers, the results from the automated AI approach weren’t very different from the analysis with a more human touch. The results aligned between 85% and 90% of the time.

It doesn’t mean the computers were perfect. Rare or hard-to-identify species sometimes tripped up the programs. SpeciesNet mistakenly classified mountain goats in Montana as domestic goats. Grizzly bears were reported in Washington, when they haven’t been there in decades.

But for many species in each of the three regions, the lightning-fast computers were as accurate as the plodding humans.

“The key question wasn’t whether the AI got every image right,” said Dan Morris, a scientist at Google who helped create SpeciesNet and is a co-author on the study. “It was whether the ecological conclusions you care about would end up being basically the same.”

If this approach finds its way out of academia, it could enable wildlife managers to get up-to-date information much more quickly about what’s happening to wild populations. Among other things, that could mean quicker alerts when an endangered species shows up somewhere, or if it’s starting to vanish.

“The big takeaway is that this doesn’t have to be a bottleneck anymore,” Thornton said of the image backlog. “If we can process data faster, we can respond faster, and that’s really what matters for conservation.”

Thornton, et. al. “Identification of camera trap images by artificial intelligence and human experts produces similar multi-species occupancy models.” Journal of Applied Ecology. May 6, 2026.

Image (based on) ©Smithsonian via Flickr

Migration and democratic decline in Central America cannot be understood separately from the intertwined impacts of US intervention, gang violence, economic instability and climate disruption. As droughts, displacement and insecurity deepen, the region faces growing pressure toward both migration and authoritarian rule.

A gathering in Paradise, California, will bring together fire-affected communities, local leaders and resilience practitioners to explore what rebuilding after catastrophe can look like beyond simply restoring the old normal.

War is a major driver of greenhouse gas emissions, yet most conflict-related emissions remain excluded from official climate accounting. Governments and international climate bodies must begin treating military emissions and the climate costs of war as central issues of accountability and justice.

Pooja Kishinani and Satakshi Gupta

An interview with visual artist Anuja Dasgupta, whose practice sits at the intersection of eco-art, ethnobotany and community. Using plant-based emulsions, cameraless photography, and repurposed wood, she creates art that refuses to represent the land, …