“As part of CSIRO’s research to end plastic waste, we’ve been developing an efficient and scalable environmental monitoring system using artificial intelligence (AI).

The system, which is part of a larger pilot with the City of Hobart, uses AI-based image recognition to track litter in waterways.
. . .

Our data revealed food packaging, beverage bottles and cups were by far the most frequently spotted litter items across all three countries.“

“The pictures come from an Earth-observation satellite orbiting 600km (372 miles) above the planet's surface.

The breakthrough could allow up to 5,000 sq km of elephant habitat to be surveyed on a single cloud-free day.

. . .

"And conservation organisations are already interested in using this to replace surveys using aircraft."

Conservationists will have to pay for access to commercial satellites and the images they capture.

But this approach could vastly improve the monitoring of threatened elephant populations in habitats that span international borders, where it can be difficult to obtain permission for aircraft surveys.”

“In 1996, Prof Shahid Naeem was part of a team of researchers who set out to value the Earth. Specifically, they were trying to establish the dollar value of all of the “ecosystem services” the planet provides to humans every year. Around $33tn, they concluded, nearly double global GDP at the time.

“The team was half ecologists and half economists. The ecologists found the exercise really scary but understood the utility of it. The economists felt nature could be valued but they disagreed about how it could be done,” Naeem says.

. . .

More than half of global GDP – $42tn (£32tn) – depends on high-functioning biodiversity, according to the insurance firm Swiss Re. The “natural capital” that sustains human life looks set to become a trillion dollar asset class: the cooling effect of forests, the flood prevention characteristics of wetlands and the food production abilities of oceans understood as services with a defined financial value. Animals, too.

The services of forest elephants are worth $1.75m for each animal, the International Monetary Fund’s Ralph Chamihas estimated; more than the $40,000 a poacher might get for shooting the mammal for ivory. Whales are worth slightly more at over $2m, he also estimates, due to their “startling” carbon capture potential, and therefore deserve better protection.“

“As a concept, it’s simple. Single Earth tokenizes land, forests, swamps, and biodiversity: any area of rich ecological significance. Companies, organizations, and eventually individuals will be able to purchase those tokens and own fractional amounts of those lands and natural resources, getting carbon offsets in return as well as ongoing ownership rights.

. . .

“Single Earth is not a fund itself,” chief technical officer Andrus Aaslaid told me. “We are not trying to become the largest landowner in the world. We are trying to provide the technology that people who own the land would be able to create profit out of it without having to sell it as raw material.”

The interesting thing about the Single Earth token is that it is nature-backed. It has real assets in the real world with real value behind it.

In some sense, that’s like gold: also a real, physical, inherently valuable store of wealth.

“Now, Imazon researchers have built an artificial intelligence algorithm to find such roads automatically. Currently, the algorithm is reaching about 70% accuracy, which rises to 87%-90% with some additional automated processing, said Souza. Analysts then confirm potential roads by examining the satellite images.

The laborious work of mapping roads by hand was not wasted -- that data was needed to train the AI algorithm. Thanks to the algorithm, Souza and his colleagues should now be able to update their map every year with relative ease.

. . .

“Large areas of road-free rainforest are important for protecting Amazonian biodiversity and isolated indigenous people, said Souza. Moreover, roads are often a harbinger of further destruction. Nearly 95% of deforestation in the Brazilian Amazon occurs within 5.5 km of a road or 1 km of a river, while about 95% of fires occur within 10 km of a road or river, according to prior research by Souza and his colleagues. Loggers and gold miners often abandon private roads when natural resources are exhausted, said Souza, whereupon farmers and ranchers make use of them for further development.

If policymakers don't consider unofficial roads, they may underestimate the harm being done to the Amazon, said Souza. The new algorithm could help provide a complete and up-to-date picture, showing where to focus efforts at rainforest protection.”

“Hundreds of previously unreported releases of raw sewage into UK rivers have been detected thanks to artificial intelligence, researchers say.

Scientists identified 926 "spill events" from two wastewater treatment plants over an 11-year period by employing machine learning.

. . .

The researchers, who published their study in the journal Clean Water, trained a computer algorithm to recognise, through the pattern of flow through a treatment plant, when a spill was happening.

The researchers say that water companies around the UK could put a similar approach in place at any plant to detect "spills that appear to be going unnoticed and unreported".”

““The inspiration for Payver came in 2017 when the UDOT executive director set a goal that it would be the first department in the country to have real-time situational awareness on our roadways, and we’ve been working on solving that problem for them,” Pittman told TechCrunch. “They want to know what’s happening and when it’s happening automatically so the public doesn’t have to be involved. So if there’s roadside debris or stop signs missing or paint lines that need to be fixed, how does the department know without the public having to call and complain or without an accident occurring?”

Blyncsy’s Payver technology works by collecting any kind of HD images and videos from a variety of sources, such as Nexar dash cameras, and analyzing the data sets with machine vision to deliver output to customers. The insights are available to transit agencies in a dashboard format, but Payver also integrates into the maintenance management software that determines a rank order of repair jobs.”

“Their system represents a fundamentally different approach to air quality monitoring compared with the stationary systems routinely used in urban areas, which the group says often fail to detect spatial heterogeneity in pollution levels across a landscape. Given their limited distribution and lack of mobility, these systems are really only a reliable indicator of the air quality directly surrounding each monitoring point, but their data are reported as though they were representative of air quality across the entire city, say the recent graduates.

“So even though they might say that your air quality is somewhat good, that may not be the case for the park right next to your home,” says Gonzalez-Diaz.

The NEET cohort’s drone system is designed to provide real-time air quality data with a 15-meter resolution that is publicly accessible through a user-friendly interface.”

“Researchers from the University of Cambridge have demonstrated how a typical touchscreen could be used to identify common ionic contaminants in soil or drinking water by dropping liquid samples on the screen, the first time this has been achieved. The sensitivity of the touchscreen sensor is comparable to typical lab-based equipment, which would make it useful in low-resource settings.

The researchers say their proof of concept could one day be expanded for a wide range of sensing applications, including for biosensing or medical diagnostics, right from the phone in your pocket.

. . .

One early application for the technology could be to detect arsenic contamination in drinking water. Arsenic is another common contaminant found in groundwater in many parts of the world, but most municipal water systems screen for it and filter it out before it reaches a household tap. However, in parts of the world without water treatment plants, arsenic contamination is a serious problem.

“In theory, you could add a drop of water to your phone before you drink it, in order to check that it’s safe,” said Daly.”

"We've found that most businesses and people have the right intentions about recycling, but oftentimes they just don't know what the proper way to recycle is," Gates, CEO of Compology, told CNN Business' Rachel Crane.

To help them do it correctly, Compology puts trash-monitoring cameras and sensors inside industrial waste containers. The cameras take photos several times each day and when the container is lifted for dumping. An accelerometer helps trigger the camera on garbage day.

AI software analyzes the images to figure out how full the container is and can also let a customer know when something is where it shouldn't be, such as a bag of trash tossed into a dumpster filled with cardboard boxes for recycling. Gates said the company's cameras can cut the amount of non-recyclable materials thrown in waste containers by as much as 80%.”

“In a recent study, a combined team from Universitat Autònoma de Barcelona (UAB), the Institute of Economic Analysis at the Spanish National Research Council and Chapman University, California successfully automated this process for the analysis of heavy weaponry impacts – with profound implications for the surveillance of conflict zones for humanitarian ends.

The team used a convolutional neural network (CNN) to automate the photo analysis, co-author André Groeger explains. Trained on sequences of satellite images from Aleppo and five other Syrian cities between 2011 and 2017, as well as human-annotated data on destruction acquired from the United Nations Satellite Team (UNOSAT), the model successfully traced the progression of war damage over the course of the civil war with a level of precision closely rivalling that of manual approaches.”

“Developing countries are most at risk from Illegal, unreported, and unregulated (IUU) fishing, with estimated actual catches in West Africa, for example, being 40 percent higher than reported catches. Worldwide, one in five wild-caught fish is likely to be illegal or unreported; the economic value of these fish never reaches the communities that are the rightful beneficiaries. Annual global losses due to this illegal activity are valued at $10 billion to $23.5 billion USD.”

. . .

Synthetic aperture radar (SAR) is one of the power tools of remote sensing, and an increasingly valuable complement to other vessel detection systems. Active satellite sensors, such as SAR, transmit radar waves to the Earth and measure the backscatter and traveling time of the signals that are reflected back from objects on the ground.

. . .

For xView3, we created a free and open large-scale dataset for maritime detection, and the computing capability required to generate, evaluate and operationalize computationally intensive AI/ML solutions at global scale. The data are consistently processed to include aligned views and relevant context above and below the ocean surface, with ground truth detections derived by combining AIS tracks, existing automated SAR analysis, and human visual detections.”

“In New York City, if you report an idler and they’re found guilty, you get 25% of the fine, which ranges from $350 to $2,000. This started in February 2018, largely thanks to the efforts of George Pakenham, a Wall Street banker and part-time clean air activist living on the Upper West Side. Pakenham was the subject of the 2012 documentary film Idle Threat: Man on Emission. In that movie, he explains that while New York had an idling ordinance that goes back to the 1970s, it was considered a “moving violation,” meaning only police could enforce it, not parking inspectors. Pakenham, with help from the New York Environmental Defense Fund, was successful in getting that changed, so the city’s army of parking inspectors could help with enforcement.”

“Their platform allows these drones, that have individual digital signatures and operate under a designated protocol, to independently assess the chemical composition of water via built-in sensors. Available parameters are as follows: – pH, oxygen levels, conductivity, temperature and other indicators of various elements.

The project is based on the idea of a decentralized network, where sensor-equipped devices collect data and send it to a distributed ledger for safe storage. In other words, it is a combination of blockchain and collective intelligence of a decentralized self-managed drone infrastructure that acts as a multi-level solution to the problem.

It is a swarm of drones that perform joint monitoring and cross verify each other’s results in a bid to eliminate false alarms and provide authentic and precise data.

Once this data is received, it is the IPFS and the Ethereum blockchain technologies that are used to secure the data. The first one guarantees that the information remains unchanged, whilst the second one stores the information on the sensors that collected the data and the time of it being registered.”

“The team pairs old technology with the latest in computing. Using a submersible digital holographic microscope, they take a 2D image. They then use a machine learning system known as a neural network to convert the 2D image into a representation of the microbiome present in the 3D environment. “Using a machine learning network, you can take a 2D image and reconstruct it almost in real time to get an idea of what the microbiome looks like in a 3D space,” says Xia.

The software can be run in a small Raspberry Pi that could be attached to the holographic microscope. To figure out how to communicate these data back to the research team, Xia drew upon her master’s degree research. In that work, under the guidance of Professor Allan Adams and Professor Joseph Paradiso in the Media Lab, Xia focused on developing small underwater communication devices that can relay data about the ocean back to researchers.

Rather than the usual $4,000, these devices were designed to cost less than $100, helping lower the cost barrier for those interested in uncovering the many mysteries of our oceans. The communication devices can be used to relay data about the ocean environment from the machine learning algorithms.

By combining these low-cost communication devices along with microscopic images and machine learning, Xia hopes to design a low-cost, real-time monitoring system that can be scaled to cover entire seaweed farms.”

“The solution utilises data from microphones and installed cameras, used as IoT sensors along the road. If an approaching vehicle exceeds the pre-determined threshold, the street-deployed microphones and cameras begin recording.

Nokia Scene Analytics adds intelligence to the event data transmitted from the sensors using a decibel-powered algorithm for audio analysis and automated number plate recognition (ANPR). This information is sent to authorities who receive quantified observations and orientations in order to make informed decisions on ‘if’ and ’how’ they will address the issue.”

“Once they’ve purchased a setup, users receive a cryptocurrency called $PLANETS in exchange for running the sensors in their homes. The coin, which currently trades for roughly 34 cents each with a $51 million dollar market cap, can be used to purchase more sensors, or resold on crypto marketplaces as a stream of passive income. For Type 4 sensors (the cheapest), the maximum reward to the user is 23 tokens per day (amounting to roughly $8 per day at current rate), but for more expensive Type 1 sensors, that rises to 166 ($45 per day). However, a cap on daily total token distribution, as well as a formula of declining rewards based on density of nearby sensors, means that the more users join, the smaller the rewards. “

“In a paper published on October 17th in Nature Communications, a group of researchers led by Jörg Müller, an ecologist at the University of Würzburg, describe a better way: have a computer do the job. Smartphone apps already exist that will identify birds, bats or mammals simply by listening to the sounds they make. Their idea was to apply the principle to conservation work.“

“The groundbreaking study, led by Global Fishing Watch, uses machine learning and satellite imagery to create the first global map of large vessel traffic and offshore infrastructure, finding a remarkable amount of activity that was previously “dark” to public monitoring systems.

The analysis reveals that about 75 percent of the world’s industrial fishing vessels are not publicly tracked, with much of that fishing taking place around Africa and south Asia. More than 25 percent of transport and energy vessel activity are also missing from public tracking systems.“

“Artificial intelligence will be used for the first time to track hedgehog populations as part of a pioneering project aimed at understanding how many of them are left in the UK and why they have suffered a decline.

Images of the prickly mammals snuffling around urban parks, private gardens, woodlands and farmland will be captured by cameras and filtered by AI trained to differentiate between wildlife and humans.

The images will then be sent to human “spotters” who will pick out those featuring hedgehogs and send them to analysts, who will record the numbers and locations.”