Where to start? A new citizen science, remote sensing approach to map recreational disturbance and other degraded areas for restoration planning

2021 ◽  
Author(s):  
Helen I. Rowe ◽  
Daniel Gruber ◽  
Mary Fastiggi
Author(s):  
Panagiotis Partsinevelos ◽  
Zacharias Agioutantis ◽  
Achilleas Tripolitsiotis ◽  
Nathaniel Schaefer

2019 ◽  
Vol 171 ◽  
pp. 104003
Author(s):  
Gino Caspari ◽  
Simon Donato ◽  
Michael Jendryke

Author(s):  
Lauren Gillespie ◽  
Megan Ruffley ◽  
Moisés Expósito-Alonso

Accurately mapping biodiversity at high resolution across ecosystems has been a historically difficult task. One major hurdle to accurate biodiversity modeling is that there is a power law relationship between the abundance of different types of species in an environment, with few species being relatively abundant while many species are more rare. This “commonness of rarity,” confounded with differential detectability of species, can lead to misestimations of where a species lives. To overcome these confounding factors, many biodiversity models employ species distribution models (SDMs) to predict the full extent of where a species lives, using observations of where a species has been found, correlated with environmental variables. Most SDMs use bioclimatic environmental variables as the dependent variable to predict a species’ range, but these approaches often rely on biased pseudo-absence generation methods and model species using coarse-grained bioclimatic variables with a useful resolution floor of 1 km-pixel. Here, we pair iNaturalist citizen science plant observations from the Global Biodiversity Information Facility with RGB-Infrared aerial imagery from the National Aerial Imagery Program to develop a deep convolutional neural network model that can predict the presence of nearly 2,500 plant species across California. We utilize a state-of-the-art multilabel image recognition model from the computer vision community, paired with a cutting-edge multilabel classification loss, which leads to comparable or better accuracy to traditional SDM models, but at a resolution of 250m (Ben-Baruch et al. 2020, Ridnik et al. 2020). Furthermore, this deep convolutional model is able to accurately predict species presence across multiple biomes of California with good accuracy and can be used to build a plant biodiversity map across California with unparalleled accuracy. Given the widespread availability of citizen science observations and remote sensing imagery across the globe, this deep learning-enabled method could be deployed to automatically map biodiversity at large scales.


Eos ◽  
2020 ◽  
Vol 101 ◽  
Author(s):  
Ghassem Asrar ◽  
Yuyu Zhou ◽  
Theresa Crimmins ◽  
Amir Sapkota

Physicians, public health officials, and experts in remote sensing and ecology recently met to identify ways that satellites, webcams, and citizen science could help them manage asthma and allergies.


2020 ◽  
Author(s):  
Raul Zurita-Milla ◽  
Iñaki Garcia de Cortazar-Atauri ◽  
Emma Izquierdo-Verdiguier

<p>Phenology is the science that studies the timing of periodic plant and animal life cycle events, as well as their causes, interrelations, and variations in space and time. Phenological information has a plethora of use and hence of users. For example, this information is often used to study climate change because phenological timings respond to changes in environmental conditions. Besides this, phenological information helps to model the water, carbon and energy cycles, is necessary to monitor and manage natural and artificial man-made ecosystems and even supports nature lovers and public health practitioners. The well-established EGU session on “Phenology and seasonality in climate change” shows the diversity of phenological research and products and brings together multiple research communities: ecologists, agronomists, foresters, climatologists, geo-information and remote sensing scientists, and of course, citizen science experts. We believe that this diversity deserves attention and propose carrying out a first analysis of users, use and usability of phenological products by interacting with the participants of this EGU session. For this we will use a presentation software that allows posing questions to the audience and collecting their views in real-time. This presentation will then provide a better view of the phenological community, including their most commonly used data sources, tools, and needs. Special attention will be paid to identify major achievements and research and/or operational gaps that can help to define a phenological agenda for this new decade.</p>


2020 ◽  
Author(s):  
Cristina Domingo-Marimon ◽  
Ester Prat ◽  
Pau Guzmán ◽  
Alaitz Zabala ◽  
Joan Masó

<p>Changes in the rhythm of nature are recognized as a useful proxy for detecting climate change and a very interesting source of data for scientists investigating its effects on the natural ecosystems. In this sense, phenology is the science that observes and studies the phases of the life cycling of living organisms and how the seasonal and interannual variations of climate affect them.</p><p>Traditionally, farmers or naturalists and scientists recorded phenological observations on paper for decades. Most of these observations correspond to practices today associated to <strong>Citizen Science.</strong> So far, in-situ observations were reduced to small traditional specimens closely located to the observer home, such as garden plants or fruit trees, butterflies, swallows or storks and, in general, the volunteers efforts were a bit biased towards accessible locations (close to the roads or urban areas). However, the strong variability of the vegetation phenology across biomes requires having more data to improve the knowledge about these changes. Despite its limitations, local, regional or national networks are dedicated to the collection of evidences on changes of vegetation phenology. At sub-national level <strong>in Catalonia</strong> (north-east of the Iberian Peninsula), the Catalan weather service deployed the FenoCat initiative and in the H2020 Groundtruth 2.0 project, <strong>RitmeNatura.cat</strong> (www.ritmenatura.cat) was co-designed as a phenological Citizen Observatory that has a community of phenology observers collecting either occasional or regular observations. It monitors 12 species and provides observers with species-phenophase guidance. Fortunately, scientists have found <strong>another ally</strong> to increase the collection of vegetation phenology data at global level: <strong>remote sensing</strong>.</p><p><strong>Remote Sensing</strong> (RS) provides several products with different spatial and spectral resolutions. MODIS with a daily revisit is ideal for detecting phenology in vegetation but in many areas of the world, a spatial resolution of 250 m (MODIS) is too coarse to account for small heterogeneous landscapes. In the other extreme high resolution imagery such as Landsat has a limited temporal resolution of only two revisiting periods per month being too low to generate a regular (and dense enough) time series once cloud cover is masked. Sentinel 2A and B with higher resolution, global coverage and 5 days temporal revisiting offer a good compromise. Still, <strong>what was obtainable from space differs methodologically from the in-situ observations and both are hardly comparable</strong>. The <strong>PhenoTandem Project</strong> (http://www.ritmenatura.cat/projects/phenotandem/index-eng.htm), part of the CSEOL initiative funded by ESA, provides an innovation consisting in co-designing a new protocol with citizen scientists that will make in-situ observations interoperate with remote sensing products by selecting the areas and habitats where traditional phenological in-situ observations done by volunteers can be also be observed in Sentinel 2 imagery</p><p>And so harmonizing citizens’ science and remote sensing observations promoted through observatories ensures a <strong>promising partnership for phenology monitoring.</strong></p>


2016 ◽  
Vol 8 (9) ◽  
pp. 726 ◽  
Author(s):  
Margaret Kosmala ◽  
Alycia Crall ◽  
Rebecca Cheng ◽  
Koen Hufkens ◽  
Sandra Henderson ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document