Tag Archives: Google Earth

Introducing Earth Engine for governments and businesses

We’re at a unique inflection point in our relationship with the planet. We face existential climate threats — a growing crisis already manifesting in extreme weather events, coupled with the loss of nature resulting from human activities such as deforestation. But at the same time, the world is mobilizing around climate action. Citizens are demanding progress, and governments and companies are making unprecedented commitments to transform how we live on this planet — from policy decisions to business practices. Over the years, one of the top climate challenges I’ve heard from businesses, governments and organizations is that they’re drowning in data but thirsty for insights.

So starting today, we’re making Google Earth Engine available to businesses and governments worldwide as an enterprise-grade service through Google Cloud. With access to reliable, up-to-date insights on how our planet is changing, organizations will be better equipped to move their sustainability efforts forward.

Google Earth Engine, which originally launched to scientists and NGOs in 2010, is a leading technology for planetary-scale environmental monitoring. Google Earth Engine combines data from hundreds of satellites and earth observation datasets with powerful cloud computing to show timely, accurate, high-resolution insights about the state of the world’s habitats and ecosystems — and how they’re changing over time. With one of the largest publicly available data catalogs and a global data archive that goes back 50 years and updates every 15 minutes, it’s possible to detect trends and understand correlations between human activities and environmental impact. This technology is already beginning to bring greater transparency and traceability to commodity supply chains, supporting climate resilience and allowing for more sustainable management of natural resources such as forests and water.

Earth Engine will be available at no charge to government researchers, least-developed countries, tribal nations and news organizations. And it will remain available at no cost for nonprofit organizations, research scientists, and other impact users for their non-commercial and research projects.

Earth Engine will also be available to startups that are a part of the Google for Startups Cloud Program. Through this initiative we provide funded startups with access to dedicated mentors, industry experts, product and technical support, and Cloud cost coverage (up to $100,000) for each of the first two years and more.

How organizations are using Earth Engine

Since we announced the preview of Earth Engine in Google Cloud last October, we’ve been working with dozens of companies and organizations across industries — from consumer packaged goods and insurance companies to agriculture technology and the public sector — to use Earth Engine’s satellite imagery and geospatial data in incredible ways.

Land cover change over time from Dynamic World

Dynamic World, a global machine learning derived land classification over time available in Earth Engine's public data catalog, was developed in partnership with World Resources Institute (WRI).

For example, Regrow, a company that helps large consumer packaged goods corporations decarbonize their agricultural practices, started using Earth Engine to report and verify regenerative and sustainable techniques. Through Earth Engine’s analysis of historical and satellite imagery, Regrow can generate granular field data at the state or country levels across millions of acres of farmland around the world.

As climate change causes shifts in biodiversity, Earth Engine is helping communities adapt to the effects of these changes, such as new mosquito outbreaks. SC Johnson partnered with Google Cloud to use Earth Engine to develop a publicly accessible, predictive model of when and where mosquito populations are emerging nationwide. The forecast accounts for billions of individual weather data points and over 60 years of mosquito knowledge in forecasting models.

Animated gif showing the Off!Cast, SC Johnson’s mosquito forecasting tool. A zip code is entered into the tool to show a 7-day forecast that indicates medium, high and very-high.

For organizations that may not have resources dedicated to working with Earth Engine, we’ve continued to grow our partner network to support them. For example, our partner NGIS worked with Rainforest Trust to get action-oriented and tailored insights that can help them conserve 39 million acres of tropical forests around the world.

It’s not too late to protect and restore a livable planet for ourselves and generations to come. Climate change experts have declared the next ten years the ‘Decade of Action’, a critical time to act in order to curb the effects of climate change. Making a global difference will require a transformational change from everyone, including businesses and governments. With Google Earth Engine, we hope to help organizations contribute to this change.

Introducing Earth Engine for governments and businesses

We’re at a unique inflection point in our relationship with the planet. We face existential climate threats — a growing crisis already manifesting in extreme weather events, coupled with the loss of nature resulting from human activities such as deforestation. But at the same time, the world is mobilizing around climate action. Citizens are demanding progress, and governments and companies are making unprecedented commitments to transform how we live on this planet — from policy decisions to business practices. Over the years, one of the top climate challenges I’ve heard from businesses, governments and organizations is that they’re drowning in data but thirsty for insights.

So starting today, we’re making Google Earth Engine available to businesses and governments worldwide as an enterprise-grade service through Google Cloud. With access to reliable, up-to-date insights on how our planet is changing, organizations will be better equipped to move their sustainability efforts forward.

Google Earth Engine, which originally launched to scientists and NGOs in 2010, is a leading technology for planetary-scale environmental monitoring. Google Earth Engine combines data from hundreds of satellites and earth observation datasets with powerful cloud computing to show timely, accurate, high-resolution insights about the state of the world’s habitats and ecosystems — and how they’re changing over time. With one of the largest publicly available data catalogs and a global data archive that goes back 50 years and updates every 15 minutes, it’s possible to detect trends and understand correlations between human activities and environmental impact. This technology is already beginning to bring greater transparency and traceability to commodity supply chains, supporting climate resilience and allowing for more sustainable management of natural resources such as forests and water.

Earth Engine will be available at no charge to government researchers, least-developed countries, tribal nations and news organizations. And it will remain available at no cost for nonprofit organizations, research scientists, and other impact users for their non-commercial and research projects.

Earth Engine will also be available to startups that are a part of the Google for Startups Cloud Program. Through this initiative we provide funded startups with access to dedicated mentors, industry experts, product and technical support, and Cloud cost coverage (up to $100,000) for each of the first two years and more.

How organizations are using Earth Engine

Since we announced the preview of Earth Engine in Google Cloud last October, we’ve been working with dozens of companies and organizations across industries — from consumer packaged goods and insurance companies to agriculture technology and the public sector — to use Earth Engine’s satellite imagery and geospatial data in incredible ways.

Land cover change over time from Dynamic World

Dynamic World, a global machine learning derived land classification over time available in Earth Engine's public data catalog, was developed in partnership with World Resources Institute (WRI).

For example, Regrow, a company that helps large consumer packaged goods corporations decarbonize their agricultural practices, started using Earth Engine to report and verify regenerative and sustainable techniques. Through Earth Engine’s analysis of historical and satellite imagery, Regrow can generate granular field data at the state or country levels across millions of acres of farmland around the world.

As climate change causes shifts in biodiversity, Earth Engine is helping communities adapt to the effects of these changes, such as new mosquito outbreaks. SC Johnson partnered with Google Cloud to use Earth Engine to develop a publicly accessible, predictive model of when and where mosquito populations are emerging nationwide. The forecast accounts for billions of individual weather data points and over 60 years of mosquito knowledge in forecasting models.

Animated gif showing the Off!Cast, SC Johnson’s mosquito forecasting tool. A zip code is entered into the tool to show a 7-day forecast that indicates medium, high and very-high.

For organizations that may not have resources dedicated to working with Earth Engine, we’ve continued to grow our partner network to support them. For example, our partner NGIS worked with Rainforest Trust to get action-oriented and tailored insights that can help them conserve 39 million acres of tropical forests around the world.

It’s not too late to protect and restore a livable planet for ourselves and generations to come. Climate change experts have declared the next ten years the ‘Decade of Action’, a critical time to act in order to curb the effects of climate change. Making a global difference will require a transformational change from everyone, including businesses and governments. With Google Earth Engine, we hope to help organizations contribute to this change.

Land cover data just got real-time

Our planet is changing dramatically in ways that are visible even from space. These changes are in part because of climate change amplifying environmental disturbances, like wildfires and floods, and human activity, like deforestation and urban development. Detailed information about these changes and their impact on people, the climate, and ecosystems can help governments and researchers develop helpful solutions and minimize their effects on issues like climate change, food insecurity and loss of biodiversity.

Historically, it’s been difficult to access detailed, up-to-date land cover data which documents how much of a region is covered with different land and water types such as wetlands, forests, agricultural crops, trees, urban development and more.

To help turn satellite imagery into more useful information for quantifying change, we worked with the World Resources Institute (WRI) to create Dynamic World. Powered by Google Earth Engine and AI Platform, Dynamic World provides global, near real-time land cover data at a ten-meter resolution, giving an unprecedented level of detail about what's on the land and how it's being used — whether it’s forests in the Amazon, agriculture in Asia, urban development in Europe or seasonal water resources in North America. With this information, people — like scientists and policymakers — can monitor and understand land and ecosystems so they can make more accurate predictions and effective plans to protect our planet in the future.

A more detailed understanding of earth’s land than ever before

Currently, most existing datasets assign a single land cover type to an area of land — like trees, built-up, crops or snow — based on what’s most prominent in a satellite image combined with an expert’s determination of the land cover. So current datasets might classify a satellite image of a city as ‘built-up,’ but visit any city and you’ll see our world is far more dynamic. While you might see lots of buildings, you’ll also see trees or even snow on the ground from a recent storm.

To create a more accurate understanding of land cover with Dynamic World, our partners at WRI identified the nine most critical land cover types we wanted to classify: water, flooded vegetation, built-up areas, trees, crops, bare ground, grass, shrub/scrub, and snow/ice. Dynamic World uses our AI and cloud computing to detect combinations of different land cover types and make conclusions about how likely it is for each of the nine types to be present in every pixel (about 1,100 square feet of land) of a satellite image.

This level of insight into how land is being used can help public, private and non-profit decision makers better understand what’s happening to the world’s land. With this knowledge, they can develop plans to protect, manage and restore land, and monitor the effectiveness of those plans using alert systems to notify when unforeseen land changes are taking place.

As Craig Hanson, Vice President of Food, Forests, Water and the Ocean at the World Resources Institute, explains: “The global land squeeze pressures us to find smarter, efficient, and more sustainable ways to use land. If the world is to produce what is needed from land, protect the nature that remains and restore some of what has been lost, we need trusted, near real-time monitoring of every hectare of the planet.”

A near real time, regularly updating dataset

Not only is our world more dynamic than individual land types, it’s also constantly changing. Current global land cover maps can take months to produce, and typically only provide land cover data on a monthly or annual basis. With our AI model analyzing Copernicus Sentinel-2 satellite images as they become available, over 5,000 Dynamic World images are produced every day, providing land cover data dating back to June 2015 to as recently as two days ago.

This means that not only is the land cover information in Dynamic World more detailed, but it's also more timely within any given day, week or month than existing datasets. This level of detail allows scientists and policymakers to detect and quantify the extent of recent events anywhere on the globe — such as snowstorms, wildfires or volcanic eruptions — within days.

A gif shows satellite imagery translated into Dynamic World imagery with lots of green area indicating tree coverage before the fire and most of that area turning yellow indicating shrub/scrub after the fire.

Satellite imagery translated into Dynamic World imagery showing land in El Dorado County, California changing from trees, indicated in green, to shrub/scrub, indicated in yellow, days after the Caldor Fire burned 221,775 acres of land beginning August 14, 2021.

A gif shows satellite imagery and Dynamic World imagery of the Okavango Delta in Botswana with increasing green and blue coloring to show changes in land cover as the delta floods in July and August and then dries from September to October

Sentinel-2 satellite imagery (left) and Dynamic World dataset (right) show typical seasonal changes in the Okavango Delta in Botswana.

Dynamic World allows researchers to build their own maps based on the outputs of our machine learning model, a major advancement in mapmaking. Researchers can combine local information with the data from Dynamic World to produce a new map, for example a map that analyzes crop harvests between particular dates. Dynamic World is also useful for understanding longer-term trends of seasonal ecosystem change, as seen in the Okavango Delta, an area that attracts thirsty wildlife when it floods in July and August and then dries from September to October.

We’re excited to put this open, freely available dataset and the methodology behind it into the hands of scientists, researchers, governments and companies. Together, we can make wiser decisions to protect, manage and restore our forests, nature and ecosystems.

Dynamic World is one of the largest global-scale land cover datasets produced to date, and is the first of its kind at 10 meter resolution in near real-time. A peer-reviewed paper about Dynamic World was published today in Nature Scientific Data. Explore the data at dynamicworld.app and access Dynamic World in Google Earth Engine and on Resource Watch.

Helping farmers with cloud technology, up close and global

Global warming brings humankind a host of challenges, from forest fires to heavy storms and desertification. Perhaps none matters more than maintaining and increasing food production. Unseasonal heat and cold snaps, new pest infestations and diseases at unexpected times, or extraordinary drought, wildfire and heavy rain, are just some of the challenges the world's food producers face today and in coming years.

Solutions to the challenges posed by climate change will likely require a two-fold approach. First, we should seek to limit the damage, through more sustainable, less carbon-intensive practices, along with carbon capturing and regenerative agriculture. Second, is to create new ways for farmers to gather and apply information about their crops, to better deal with the challenging new realities of growing food.

Paradoxically, this global challenge calls for better focus on local farming conditions. Farmers worldwide know the particulars of their soil, crops, and rainfall. Farmers can benefit from a better read on how unexpected conditions are affecting their specific farms, so they can take the right steps of prevention and remediation for their farms.

This is why Google Cloud is proud and excited to be working with companies like Agrology, a Virginia-based public benefit company who developed a predictive agriculture system that uses machine learning models, IoT sensors and Artificial Intelligence to deliver farmers timely predictions and insights on everything from temperature, rainfall, and soil conditions, to reducing greenhouse gas emissions from nutrient and fertilizer applications.

Agrology was founded in 2019 with a National Science Foundation SBIR Award, and has gone on to service a number of specialty farms across the country from California to Virginia. The present focus is in wine grape growing and specialty crops, where local soil and climate conditions are particularly important and are under extreme threat. Over time, Agrology will roll out their custom data-driven platform and localized approach to many more farms.

"Early on, we met an apple grower who told us that a weather report from 75 miles away wasn't helping him anymore with figuring out how to apply pesticides, there was too much variation," says Adam Koeppel, Agrology's chief executive. "No farmer wants to overspray pesticides. We started thinking about how holistic agriculture is, and how site-specific it should be."

Agrology developed a custom platform with agricultural sensors which continuously gather a range of data above and below ground. This data is combined with other information, including highly local weather forecasts and macro information like baseline satellite data Agrology then makes sense of all the influences and interactions with TensorFlow, our Machine Learning platform. Google Earth helps the team figure out where to lay out their hardware and wireless gateways so that the team has the necessary tools to deliver data from remote locations to the cloud. “That's a big deal”, says Tyler Locke, Agrology's Chief Technology Officer. "Rural agriculture areas tend to be underserved in technology and infrastructure most of the time," he says. "Farmers want technology to help solve their climate change challenges, but they’ve had a hard time getting it."

We're also pleased to play a role in helping Agrology develop its first data models. Kevin Kelly, Agrology's head of Engineering and Machine Learning, taught himself on Google Colab, a dynamic tool for learning and building and sharing Machine Learning solutions. "Like most engineers, I'm a hands-on learner," Kelly says. "With Colab I was able to step through and execute every line of code, change it, and run it again to see how it affected the output."

Using TensorFlow, Kelly adds, was likewise an easy choice, since "studying model architectures and reading blogs, I found that AI researchers, applications engineers and even hobbyists interested in problems like ours – lots of quality data, lots of interactions among seemingly disparate data sets – overwhelmingly used Tensorflow and Keras to develop their models."

Agrology's cutting-edge approach to agriculture is already showing benefits to its clients, and the team is confident its approach and learnings can scale to an even bigger impact.

"We believe we can help maintain and improve yields, but even more," says Adam. "We are finding ways to help farmers with regenerative agriculture, understanding their ability to enhance soil carbon sequestration with the right crops, better water use, or fertilizer applications that avoid releasing excessive greenhouse gasses. The rate at which the climate is changing is driving growers to alter how they farm and do business. There simply aren’t enough farmers and agronomists, and technology can help growers thrive in spite of the growing challenges.”

Mosquitos get the swat with new forecasting technology

Mosquitoes aren’t just the peskiest creatures on Earth; they infect more than 700 million people a year with dangerous diseases like Zika, Malaria, Dengue Fever, and Yellow Fever. Prevention is the best protection, and stopping mosquito bites before they happen is a critical step.

SC Johnson — a leading developer and manufacturer of pest control products, consumer packaged goods, and other professional products — has an outsized impact in reducing the transmission of mosquito-borne diseases. That’s why Google Cloud was honored to team up with one of the company’s leading pest control brands, OFF!®, to develop a new publicly available, predictive model of when and where mosquito populations are emerging nationwide. 

As the planet warms and weather changes, OFF! noticed month-to-month and year-to-year fluctuations in consumer habits at a regional level, due to changes in mosquito populations. Because of these rapid changes, it’s difficult for people to know when to protect themselves. The OFF!Cast Mosquito Forecast™, built on Google Cloud and available today, will predict mosquito outbreaks across the United States, helping communities protect themselves from both the nuisance of mosquitoes and the dangers of mosquito-borne diseases — with the goal of expanding to other markets, like Brazil and Mexico, in the near future. 

An animated gif titled ‘Mosquito Habitat: Current & Projected’ shows projections for the number of months per year when disease transmission from the Aedes aegypti mosquito is possible as it increases over time from 2019 to 2080. The projection is based on a worst-case scenario in which the impact of climate change is unmitigated.

Source: Sadie J. Ryan, Colin J. Carlson, Erin A. Mordecai, and Leah R. Johnson

With the OFF!Cast Mosquito Forecast™, anyone can get their local mosquito prediction as easily as a daily weather update. Powered by Google Cloud’s geospatial and data analytics technologies, OFF!Cast Mosquito Forecast is the world’s first public technology platform that predicts and shares mosquito abundance information. By applying data that is informed by the science of mosquito biology, OFF!Cast accurately predicts mosquito behavior and mosquito populations in specific geographical locations.

Starting today, anyone can easily explore OFF!Cast on a desktop or mobile device and get their local seven-day mosquito forecast for any zip code in the continental United States. People can also sign up to receive a weekly forecast. To make this forecasting tool as helpful as possible, OFF! modeled its user interface after popular weather apps, a familiar frame of reference for consumers.

Animated gif shows how you enter your zip code into the Off!Cast Mosquita forecast to see a 7-day mosquito forecast for your area, similar to a weather forecast. It shows the mosquito forecast range from medium, high to very high.

SC Johnon’s OFF!Cast platform gives free, accurate and local seven-day mosquito forecasts for zip codes across the continental United States.

The technology behind the OFF!Cast Mosquito Forecast

To create this first-of-its-kind forecast, OFF! stood up a secure and production-scale Google Cloud Platform environment and tapped into Google Earth Engine, our cloud-based geospatial analysis platform that combines satellite imagery and geospatial data with powerful computing to help people and organizations understand how the planet is changing. 

The OFF!Cast Mosquito Forecast is the result of multiple data sources coming together to provide consumers with an accurate view of mosquito activity. First, Google Earth Engine extracts billions of individual weather data points. Then, a scientific algorithm co-developed by the SC Johnson Center for Insect Science and Family Health and Climate Engine experts translates that weather data into relevant mosquito information. Finally, the collected information is put into the model and distilled into a color-coded, seven-day forecast of mosquito populations. The model is applied to the lifecycle of a mosquito, starting from when it lays eggs to when it could bite a human.

It takes an ecosystem to battle mosquitos

Over the past decade, academics, scientists and NGOs have used Google Earth Engine and its earth observation data to make meaningful progress on climate research, natural resource protection, carbon emissions reduction and other sustainability goals. It has made it possible for organizations to monitor global forest loss in near real-time and has helped more than 160 countries map and protect freshwater ecosystems. Google Earth Engine is now available in preview with Google Cloud for commercial use.

Our partner, Climate Engine, was a key player in helping make the OFF!Cast Mosquito Forecast a reality. Climate Engine is a scientist-led company that works with Google Cloud and our customers to accelerate and scale the use of Google Earth Engine, in addition to those of Google Cloud Storage and BigQuery, among other tools. With Climate Engine, OFF! integrated insect data from VectorBase, an organization that collects and counts mosquitoes and is funded by the U.S. National Institute of Allergy and Infectious Diseases.

The model powering the OFF!Cast Mosquito Forecast combines three inputs — knowledge of a mosquito’s lifecycle, detailed climate data inputs, and mosquito population counts from more than 5,000 locations provided by VectorBase. The model’s accuracy was validated against precise mosquito population data collected over six years from more than 33 million mosquitoes across 141 different species at more than 5,000 unique trapping locations.

A better understanding of entomology, especially things like degree days and how they affect mosquito populations, and helping communities take action is critically important to improving public health.

A version of this blogpost appeared on the Google Cloud blog.

This World Wildlife Day, the key word is adapt

Wolverines are stocky, energetic carnivores who resemble small bears. These animals travel up to 15 miles a day and summit peaks in the wildest lands. Currently, their habitat range includes parts of the northern U.S. and Canada where they have access to huge swaths of remote land with abundant winter and spring snowpack to build dens for their baby kits. However, like other species across the world, their habitat is at risk of shrinking due to climate change.

As entire habitats change, land managers and policymakers need to be able to make local land-use decisions that support regionally important species and ecosystems. Cloud-based mapping tools, like TerrAdapt which launched to the public today on World Wildlife Day, can help prioritize areas for conservation actions — like habitat restoration, increasing protection status, and building wildlife crossings. TerrAdapt uses satellite monitoring technology powered by Google Earth Engine and Google Cloud Platform to project habitat conditions given future climate and land-use scenarios.

Using TerrAdapt to monitor wolverines

It’s initially being developed in the Cascadia region — which spans part of Washington in the U.S and British Columbia in Canada — to model habitat ranges for species like the wolverine, as well as the fisher, grizzly bear, greater sage-grouse and Canada lynx. Working with the Cascadia Partner Forum and the Washington Department of Natural Resources, the TerrAdapt team partnered with leading wolverine biologists to model changes in the wolverines’ habitat and connectivity between 1990 to 2100.

Areas in orange and red show the shrinking of montane wet forest habitats where snow-dependent wildlife like the wolverine live, projected to 2100.

Areas in orange and red show the shrinking of montane wet forest habitats where snow-dependent wildlife like the wolverine live, projected to 2100.

According to this model, wolverines and other snow-dependent species are expected to see significant changes to their habitat — especially when climate change scenarios are factored into the mix. Looking forward to 2100, there is little remaining wolverine habitat in the U.S.

Projections of how the suitable habitat for snow-dependent species changes from 1990 to 2100 based on the amount of liquid water contained in the snowpack, or SWE, under a “business as usual” climate scenario.

Projections of how the suitable habitat for snow-dependent species changes from 1990 to 2100 based on the amount of liquid water contained in the snowpack, or SWE, under a “business as usual” climate scenario.

Conservationists are concerned we’re not adequately preparing to protect the wolverines and their habitat which is also home to other species of animals and plants. In 2020, the decision to federally list the wolverine as threatened under the Endangered Species Act was rejected on the basis that there’s still sufficient snowpack.

Moving forward, land managers and policymakers can use TerrAdapt projections to better inform decisions like this. Carly Vynne, TerrAdapt co-founder and Director of Biodiversity and Climate at RESOLVE says that TerrAdapt helps them keep these animals on the landscape. “TerrAdapt allows us to visualize future scenarios and plan management responses,” she says. “This helps make sure that our region is as resilient as possible for wolverines and the other plants, animals, and human communities that depend on our natural landscapes.”

Making decisions that benefit the planet

The ability to use findings to inform conservation decisions and policy needs to grow. Equipped with information from TerrAdapt on how our current and future land-use decisions affect our natural world, we can increase ecological resilience to climate change risks and make land-use decisions that benefit our planet.

Explore how Google’s technology, such as Google Earth Engine, is being used to help decision makers improve resilience and adapt to climate change. And learn more about how TerrAdapt is helping us plan for a positive future with wolverines in this short video.

This archaeologist fights tomb raiders with Google Earth

In the summer, Dr. Gino Caspari’s day starts at 5:30 a.m. in Siberia, where he studies the ancient Scythians with the Swiss National Science Foundation. There, he looks for burial places of these nomadic warriors who rode through Asia 2,500 years ago. The work isn’t easy, from dealing with extreme temperatures, to swamps covered with mosquitos. But the biggest challenge is staying one step ahead of tomb raiders.

It’s believed that more than 90% of the tombs — called kurgans — have already been destroyed by raiders looking to profit off what they find, but Gino is looking for the thousands he believes remain scattered across Russia, Mongolia and Western China. To track his progress, he began mapping these burial sites using Google Earth. “There’s a plethora of open data sources out there, but most of them don’t have the resolution necessary to detect individual archaeological structures,” Dr. Caspari says, pointing out that getting quality data is also very expensive. “Google Earth updates high-res data across the globe, and, especially in remote regions, it was a windfall for archaeologists. Google Earth expanded our possibilities to plan surveys and understand cultural heritage on a broader geographic scale.”

While Google Earth helped Dr. Caspari plan his expeditions, he still couldn’t stay ahead of the looters. He needed to get there faster. That’s when he met data scientist Pablo Crespo and started using another Google tool, TensorFlow.

“Since I started my PhD in 2013, I have been interested in automatic detection of archaeological sites from remote sensing data,” Gino says. “It was clear we needed to look at landscapes and human environmental interaction to understand past cultures. The problem was that our view was obscured by a lack of data and a focus on individual sites.” Back then, he tried some simple automatization processes to detect the places he needed for his research with the available technology, but only got limited results. In 2020, though, Gino and Pablo created a machine learning model using TensorFlow that could analyze satellite images they pulled from Google Earth. This model would look for places on the images that had the characteristics of a Scythian tomb.

The progress in the field of machine learning has been insanely fast, improving the quality of classification and detection to a point where it has become much more than just a theoretical possibility. Google’s freely available technologies have help

This technology sped up the discovery process for Gino, giving him an advantage over looters and even deterioration caused by climate change.

“Frankly, I think that without these tools, I probably wouldn’t have gotten this far in my understanding of technology and what it can do to make a difference in the study of our shared human past,” Gino says. “As a young scholar, I just lack the funds to access a lot of the resources I need. Working with Pablo and others has widened my perspective on what is possible and where we can go.”

Technology solutions have given Dr. Caspari’s work a new set of capabilities, supercharging what he’s able to do. And it’s also made him appreciate the importance of the human touch. “The deeper we dive into our past with the help of technology, the more apparent it becomes how patchy and incomplete our knowledge really is,” he says. “Technology often serves as an extension of our senses and mitigates our reality. Weaving the fabric of our reality will remain the task of the storyteller in us.”

This archaeologist fights tomb raiders with Google Earth

In the summer, Dr. Gino Caspari’s day starts at 5:30 a.m. in Siberia, where he studies the ancient Scythians with the Swiss National Science Foundation. There, he looks for burial places of these nomadic warriors who rode through Asia 2,500 years ago. The work isn’t easy, from dealing with extreme temperatures, to swamps covered with mosquitos. But the biggest challenge is staying one step ahead of tomb raiders.

It’s believed that more than 90% of the tombs — called kurgans — have already been destroyed by raiders looking to profit off what they find, but Gino is looking for the thousands he believes remain scattered across Russia, Mongolia and Western China. To track his progress, he began mapping these burial sites using Google Earth. “There’s a plethora of open data sources out there, but most of them don’t have the resolution necessary to detect individual archaeological structures,” Dr. Caspari says, pointing out that getting quality data is also very expensive. “Google Earth updates high-res data across the globe, and, especially in remote regions, it was a windfall for archaeologists. Google Earth expanded our possibilities to plan surveys and understand cultural heritage on a broader geographic scale.”

While Google Earth helped Dr. Caspari plan his expeditions, he still couldn’t stay ahead of the looters. He needed to get there faster. That’s when he met data scientist Pablo Crespo and started using another Google tool, TensorFlow.

“Since I started my PhD in 2013, I have been interested in automatic detection of archaeological sites from remote sensing data,” Gino says. “It was clear we needed to look at landscapes and human environmental interaction to understand past cultures. The problem was that our view was obscured by a lack of data and a focus on individual sites.” Back then, he tried some simple automatization processes to detect the places he needed for his research with the available technology, but only got limited results. In 2020, though, Gino and Pablo created a machine learning model using TensorFlow that could analyze satellite images they pulled from Google Earth. This model would look for places on the images that had the characteristics of a Scythian tomb.

The progress in the field of machine learning has been insanely fast, improving the quality of classification and detection to a point where it has become much more than just a theoretical possibility. Google’s freely available technologies have help

This technology sped up the discovery process for Gino, giving him an advantage over looters and even deterioration caused by climate change.

“Frankly, I think that without these tools, I probably wouldn’t have gotten this far in my understanding of technology and what it can do to make a difference in the study of our shared human past,” Gino says. “As a young scholar, I just lack the funds to access a lot of the resources I need. Working with Pablo and others has widened my perspective on what is possible and where we can go.”

Technology solutions have given Dr. Caspari’s work a new set of capabilities, supercharging what he’s able to do. And it’s also made him appreciate the importance of the human touch. “The deeper we dive into our past with the help of technology, the more apparent it becomes how patchy and incomplete our knowledge really is,” he says. “Technology often serves as an extension of our senses and mitigates our reality. Weaving the fabric of our reality will remain the task of the storyteller in us.”

How photos can curb illegal deforestation in the Amazon

As of 2020, Brazil continues to lead the world in primary forest loss with an increase of 25% year over year. In the Amazon, the clear-cut deforestation rate is at its highest in over 10 years. Instituto Socioambiental (ISA) is a Brazilian nonprofit founded in 1994 to promote solutions to this crisis and other social and environmental issues. With a focus on the defense of the environment, cultural heritage, and human rights, ISA promotes solutions for indigenous peoples and other traditional communities in Brazil.

Watch this short documentary about their impact, how they use drone footage and Google Earth to prevent deforestation, and learn more about the role of indigenous communities in protecting local forests and biodiversity.

Helping fashion brands make more sustainable decisions

The fashion industry is one of the largest contributors to the global climate and ecological crisis — accounting for up to 8% of global greenhouse gas emissions. Much of this impact occurs at the raw materials stage of the supply chain, like when cotton is farmed or trees are cut down to create viscose. But when brands source these materials, they often have little to no visibility on the environmental impact of them.

In 2019, we set out to create a tool that would give companies the data they need to make more responsible sourcing decisions. Today we’re announcing the first version of the Global Fibre Impact Explorer (GFIE), and we’re inviting other brands to get involved. The tool, which is built on Google Earth Engine and uses Google Cloud computing, assesses the environmental risk of different fibers across regions as it relates to environmental factors such as air pollution, biodiversity, climate and greenhouse gasses, forestry and water use.

With this tool, brands will easily be able to identify environmental risks across more than 20 fiber types — including natural, cellulosic and synthetics materials.The tool will also provide brands with recommendations for targeted and regionally specific risk reduction activities including opportunities to work with farmers, producers and communities, such as investing in regenerative agriculture practices

The GFIE dashboard where brands can upload their fiber portfolio data and get recommendations to reduce risk across key environmental categories.

The GFIE dashboard where brands can upload their fiber portfolio data and get recommendations to reduce risk across key environmental categories.

Spooling it all together: Working with fashion brands and conservation experts

We worked with Stella McCartney, a luxury fashion brand and leader in sustainability, to understand the industry's needs and to test the platform. Using the tool alongside their existing sustainability efforts, Stella McCartney’s team was able to identify cotton sources in Turkey that were facing increased water and climate risks. This affirms the need for investing in local farming communities that focus on regenerative practices, such as water management and soil regeneration. Other brands and retailers — including Adidas, Allbirds, H&M Group and VF Corporation — have helped test and refine the tool to make sure it can be useful to everyone in the industry. And an external council of global experts have reviewed the GFIE methodology and data.

The GFIE was born out of a partnership between Google and the WWF, and is built to complement existing tools focused on industry impact and risk analysis. With the initial development phase complete, Google and WWF are now transitioning GFIE to Textile Exchange, a global non-profit focused on positively impacting climate through accelerating the use of preferred fibers across the global textile industry. As the official host of the GFIE, Textile Exchange will continue the development of the tool, onboard new brands and work towards an industry launch in 2022.

If you’re a part of a fashion brand or industry group and want access to this tool, please register your interest at globalfibreimpact.com.