PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Scientists use machine learning to predict diversity of tree species in forests

Scientists use machine learning to predict diversity of tree species in forests
2024-07-16
(Press-News.org) A collaborative team of researchers led by Ben Weinstein of the University of Florida, Oregon, US, used machine learning to generate highly detailed maps of over 100 million individual trees from 24 sites across the U.S., publishing their findings July 16th in the open-access journal PLOS Biology. These maps provide information about individual tree species and conditions, which can greatly aid conservation efforts and other ecological projects. 

Ecologists have long collected data on tree species to better understand a forest’s unique ecosystem. Historically, this has been done by surveying small plots of land and extrapolating those findings, though this cannot account for the variability across the whole forest. Other methods can cover broader areas, but often struggle to categorize individual trees.

To generate large and highly detailed forest maps, the researchers trained a type of machine learning algorithm called a deep neural network using images of the tree canopy and other sensor data taken by plane. These training data covered 40,000 individual trees and, like all the data used in this study, were provided by the National Ecological Observatory Network.

The deep neural network was able to classify most common tree species with 75 to 85 percent accuracy. Additionally, the algorithm could also provide other important analyses, such as reporting which trees are alive or dead.

The researchers found that the deep neural network had the highest accuracy in areas with more open space in the tree canopy and performed best when categorizing conifer tree species, such as pines, cedars, and redwoods. The network also performed best in areas with lower species diversity. Understanding the strengths of the algorithm can be useful for applying these methods in a variety of forest ecosystems.

The researchers also uploaded their models’ predictions to Google Earth Engine so that their findings can aid other ecological research. The researchers add, “The diversity of overlapping datasets will foster richer areas of understanding for forest ecology and ecosystem functioning.”

The authors add, “Our aim is to provide researchers with the first broad scale maps of tree species diversity from ecosystems across the United States. These canopy tree maps can be updated with new data collected at each site. By collaborating with researchers across NEON sites we can build better and better predictions over time.”

#####

In your coverage, please use this URL to provide access to the freely available paper in PLOS Biology: http://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3002700

Citation: Weinstein BG, Marconi S, Zare A, Bohlman SA, Singh A, Graves SJ, et al. (2024) Individual canopy tree species maps for the National Ecological Observatory Network. PLoS Biol 22(7): e3002700. https://doi.org/10.1371/journal.pbio.3002700

Author Countries: United States

Funding: see manuscript

END


[Attachments] See images for this press release:
Scientists use machine learning to predict diversity of tree species in forests

ELSE PRESS RELEASES FROM THIS DATE:

Machine learning helps define new subtypes of Parkinson’s disease

2024-07-16
Researchers at Weill Cornell Medicine have used machine learning to define three subtypes of Parkinson’s disease based on the pace at which the disease progresses. In addition to having the potential to become an important diagnostic and prognostic tool, these subtypes are marked by distinct driver genes. If validated, these markers could also suggest ways the subtypes can be targeted with new and existing drugs. The research was published on July 10 in npj Digital Medicine. “Parkinson’s disease is highly heterogeneous, which means that ...

Weight loss influences risky decisions in obesity

2024-07-16
People who are severely overweight (obese) not only exhibit altered risk behavior, but also changes in their metabolism and psyche. It was previously assumed that severely obese people are more impulsive and show an increased willingness to take a risk. Scientists from the DZD partner German Institute of Human Nutrition Potsdam-Rehbrücke (DIfE) have now investigated whether massive weight loss leads to an improvement in metabolic and psychological states and whether decision-making is improved. The results were published in the journal 'Clinical Nutrition'. Being overweight can cause metabolism to slip Our behavior depends on many factors. ...

EurekAlert! Travel Awards recognize early-career science journalists in Eastern Europe for the first time

EurekAlert! Travel Awards recognize early-career science journalists in Eastern Europe for the first time
2024-07-16
The winners of the 2024 EurekAlert! Travel Awards are Pavla Hubálková, a Czech science journalist at WIRED.CZ, and Iris Duțescu, a Romanian freelance science journalist.   An independent panel of three judges with regional science journalism expertise selected the winners. Both awardees will receive travel support from EurekAlert! to attend the 2025 Annual Meeting of the American Association for the Advancement of Science (AAAS) in Boston, Mass., where they will have opportunities to cover the latest scientific research and make connections with scientists ...

Etiologies of splenic venous hypertension

Etiologies of splenic venous hypertension
2024-07-16
Splenic venous hypertension (SVH), also known as left-sided portal hypertension, is a rare condition characterized by upper gastrointestinal (GI) bleeding in the absence of liver disease. This condition arises due to increased pressure in the splenic vein (SV), causing blood to drain through the short gastric veins to the stomach, leading to the dilation of submucosal structures and the formation of gastric varices. Unlike traditional portal venous hypertension (PVH), SVH does not involve elevated pressures in the main portal vein and is primarily an extrahepatic condition. Diagnosing SVH requires ...

Breakthrough in quantum microscopy: Stuttgart researchers are making electrons visible in slow motion

Breakthrough in quantum microscopy: Stuttgart researchers are making electrons visible in slow motion
2024-07-16
"With the method we developed, we can make things visible that no one has seen before," says Prof. Sebastian Loth, Managing Director of the Institute for Functional Matter and Quantum Technologies (FMQ) at the University of Stuttgart. "This makes it possible to settle questions about the movement of electrons in solids that have been unanswered since the 1980s." However, the findings of Loth's group are also of very practical significance for the development of new materials. Tiny changes with macroscopic consequences In ...

E-sales of a wild bat sold as décor threaten species

E-sales of a wild bat sold as décor threaten species
2024-07-16
A fiery orange bat, its wings folded and tiny teeth forever bared on its fuzzy face, is mounted inside a 6-inch, black coffin. Its retail price: $59. Or, for $140, you can get one framed with its black and orange wings spread, deliverable in two days. Despite declining numbers in the wild, hundreds of specimens like this of Kerivoula picta—or painted woolly bat—are being sold on Etsy, eBay and Amazon as jewelry, Halloween decorations, and jarred curios.  A study published July 9 in the European Journal of Wildlife Research found “abundant evidence that ...

Social media polls deliberately skew political realities of 2016, 2020 US presidential elections, finds research team led by UMass Amherst

Social media polls deliberately skew political realities of 2016, 2020 US presidential elections, finds research team led by UMass Amherst
2024-07-16
AMHERST, Mass. – Informal political polls conducted on X/Twitter during both the 2016 and 2020 U.S. presidential elections were significantly skewed by questionable votes, many of which may have been purchased from troll farms. This conclusion, reached by a team of scientists led by Przemyslaw (Przemek) Grabowicz, research assistant professor at the University of Massachusetts Amherst, shows that X/Twitter’s poll system deliberately reports biased public vote counts. On average, the results of such questionable polls favored Donald Trump over Joe Biden, 58% to 42% in a head-to-head comparison, during 2020. The team additionally found that ...

Unique characteristics of previously unexplored protein discovered

Unique characteristics of previously unexplored protein discovered
2024-07-16
An international research collaboration, led by Prof. Dr. Robert Grosse (Centre for Integrative Biological Signalling Studies and Institute of Clinical and Experimental Pharmacology and Toxicology, University of Freiburg), Dr. Libor Macurek (Institute of Molecular Genetics, Czech Academy of Sciences, Prague) and Dr. Zdenek Lansky (Institute of Biotechnology, Czech Academy of Sciences, Prague) has uncovered a new mechanism of the crosstalk between microtubules and actin cytoskeleton during cell division and ...

Alcoholic liver disease in China: A disease influenced by complex social factors that should not be neglected

Alcoholic liver disease in China: A disease influenced by complex social factors that should not be neglected
2024-07-16
Alcoholic liver disease (ALD) is a major cause of liver-related morbidity and mortality globally. Chronic alcohol consumption, a primary driver of ALD, leads to a spectrum of liver conditions ranging from fatty liver to cirrhosis and hepatocellular carcinoma. In China, the incidence of ALD has been rising at an alarming rate, reflecting the country's rapid economic growth and changing social norms around alcohol consumption. This paper explores the complex social factors influencing ALD in China, the complications ...

Foreign direct investments may fuel tropical deforestation

Foreign direct investments may fuel tropical deforestation
2024-07-16
Foreign direct investments (FDI) in tropical countries in extractive industries like mining, logging and fossil fuels have a long, environmentally destructive track record in tropical countries. Are FDI in food systems another extractive industry? Highlights: Foreign direct investment (FDI) in food systems are a major contributor to deforestation in tropical countries, an advanced machine learning model shows Laws requiring deforestation-free exports are welcome but likely address only a fraction of forest loss potentially linked to FDI in food systems in domestic markets Better regulation of FDI in domestic food production is needed to save more forest ...

LAST 30 PRESS RELEASES:

Brain stimulation can boost math learning in people with weaker neural connections

Inhibiting enzyme could halt cell death in Parkinson’s disease, study finds

Neurotechnology reverses biological disadvantage in maths learning

UNDER EMBARGO: Neurotechnology reverses biological disadvantage in maths learning

Scientists target ‘molecular machine’ in the war against antimicrobial resistance

Extending classical CNOP method for deep-learning atmospheric and oceanic forecasting

Aston University research: Parents should encourage structure and independence around food to support children’s healthy eating

Thunderstorms are a major driver of tree death in tropical forests

Danforth Plant Science Center adds two new faculty members

Robotic eyes mimic human vision for superfast response to extreme lighting

Racial inequities and access to COVID-19 treatment

Residential segregation and lung cancer risk in African American adults

Scientists wipe out aggressive brain cancer tumors by targeting cellular ‘motors’

Capturability distinction analysis of continuous and pulsed guidance laws

CHEST expands Bridging Specialties Initiative to include NTM disease and bronchiectasis on World Bronchiectasis Day

Exposure to air pollution may cause heart damage

SwRI, UTSA selected by NASA to test electrolyzer technology aboard parabolic flight

Prebiotics might be a factor in preventing or treating issues caused by low brain GABA

Youngest in class at higher risk of mental health problems

American Heart Association announces new volunteer leaders for 2025-26

Gut microbiota analysis can help catch gestational diabetes

FAU’s Paulina DeVito awarded prestigious NSF Graduate Research Fellowship

Champions for change – Paid time off initiative just made clinical trials participation easier

Fentanyl detection through packaging

Prof. Eran Meshorer elected to EMBO for pioneering work in epigenetics

New 3D glacier visualizations provide insights into a hotter Earth

Creativity across disciplines

Consequences of low Antarctic sea ice

Hear here: How loudness and acoustic cues help us judge where a speaker is facing

A unique method of rare-earth recycling can strengthen the raw material independence of Europe and America

[Press-News.org] Scientists use machine learning to predict diversity of tree species in forests