We are witnessing a rapid increase in news sending the message that drone seeding is a promising technological solution to implement forest restoration at large spatial scales. However, there are ...neither reports regarding success nor peer‐reviewed studies to support these assertions. Once in the ground, the seeds and the seedlings and saplings that they generate have to face biotic and abiotic hazards that can strongly reduce regeneration potential. Successful forest restoration, therefore, cannot be achieved by simply dropping seeds from the air. We summarize some aspects to take into account before considering drone seeding as an efficient and widely applicable technology for forest restoration. A first step should be to increase the precision of drone seeding—contrary to the current massive firing of seeds—in order to concentrate the efforts in the best microsites for establishment and reduce the number of seeds needed and the cost of the whole operation.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
•We used freely available deep learning models to analyse social media content in two distinct Iberian areas.•Our models allowed accurate classification of nature attributes underlying cultural ...ecosystem services (CES)•In Peneda-Gerês (Portugal) results showed preference for living systems supporting aesthetics appreciation.•Conversely, elements resonant in terms of culture and heritage were preferred in Sierra-Nevada (Spain).•We demonstrate that deep learning can be used for assessing CES-relevant content from crowdsourced data.
Crowdsourced social media data has become popular for assessing cultural ecosystem services (CES). Nevertheless, social media data analyses in the context of CES can be time consuming and costly, particularly when based on the manual classification of images or texts shared by people. The potential of deep learning for automating the analysis of crowdsourced social media content is still being explored in CES research. Here, we use freely available deep learning models, i.e., Convolutional Neural Networks, for automating the classification of natural and human (e.g., species and human structures) elements relevant to CES from Flickr and Wikiloc images. Our approach is developed for Peneda-Gerês (Portugal) and then applied to Sierra Nevada (Spain). For Peneda-Gerês, image classification showed promising results (F1-score ca. 80%), highlighting a preference for aesthetics appreciation by social media users. In Sierra Nevada, even though model performance decreased, it was still satisfactory (F1-score ca. 60%), indicating a predominance of people’s pursuit for cultural heritage and spiritual enrichment. Our study shows great potential from deep learning to assist in the automated classification of human-nature interactions and elements from social media content and, by extension, for supporting researchers and stakeholders to decode CES distributions, benefits, and values.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
A particular challenge in Natural Language Processing is the disambiguation of polysemic words. The great availability, diversity and the speed of changing of the data from on-line sources force the ...development of disambiguation systems with a reduced dependency on linguistic resources. We argue that the contextual neural encoding of a specific entity avoids the need of using external linguistic resources like knowledge bases. Hence, we propose a neural network architecture grounded in the use of Long Short-Term Memory Recurrent Neural Network for encoding the context of a target geographical entity, specifically Two k-Contextual Windows model for the disambiguation of the geographical entity Granada. We generate two annotated corpora of texts from social media written in English and Spanish, which we use to evaluate our proposal. The results show that our claim holds.
•A challenge in Natural Language Processing is the disambiguation of polysemic words.•Named entities are also polysemic, so their disambiguation is required.•Disambiguation methods highly depend on linguistic resources.•We propose a deep recurrent neural network that does not use any linguistic resourse.•The results show that our model can disambiguate the target entity.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Aerial seeding with drones has great potential in forest restoration but faces enormous challenges to be efficient and scalable. Current protocols use blanket seeding throughout the area to be ...restored, meaning a high demand for seed since many seeds arrive in sites unsuitable for establishment. High precision seeding directed to safe microsites at submeter scale could reduce seed use per hectare, reducing economic and ecological costs, while increasing establishment success. Here, we propose an alternative, precision approach to make drone seeding more successful and efficient. This requires (1) submeter‐scale selection of target microsites for seeding founded in ecological knowledge; (2) high‐resolution remote sensing imagery to train artificial intelligence (AI) systems in target microsite recognition; and (3) process automation by transferring target microsite coordinates from the AI system to the drone. This will reduce seed inputs per unit area, seedling establishment failure risks, and drone operation costs.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Deep learning has advanced the content analysis of digital data, unlocking opportunities for detecting, mapping, and monitoring invasive species. Here, we tested the ability of open source ...classification and object detection models (i.e., convolutional neural networks: CNNs) to identify and map the invasive plant Cortaderia selloana (pampas grass) in mainland Portugal. CNNs were trained over citizen science images and then applied to social media content (from Flickr, Twitter, Instagram, and Facebook), allowing to classify or detect the species in over 77% of situations. Images where the species was identified were mapped, using their georeferenced coordinates and time stamp, showing previously unreported occurrences of C. selloana, and a tendency for the species expansion from 2019 to 2021. Our study shows great potential from deep learning, citizen science and social media data for the detection, mapping, and monitoring of invasive plants, and, by extension, for supporting follow-up management options.
•We used open source deep learning models to analyse online content in Portugal.•Our models allowed accurate classification and detection of Cortaderia selloana.•Georeferenced images showed a tendency for the species expansion from 2019 to 2021.•We demonstrate that deep learning can be used for monitoring invasive alien plants.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•It provides an overview of the most popular ensemble methods.•It analyzes several fusion schemes using MNIST as guiding thread.•It introduces MNIST-NET10, a complex heterogeneous fusion ...architecture.•MNIST-NET10 reaches a new record in MNIST with only 10 misclassified images.
Ensemble methods have been widely used for improving the results of the best single classification model. A large body of works have achieved better performance mainly by applying one specific ensemble method. However, very few works have explored complex fusion schemes using heterogeneous ensembles with new aggregation strategies. This paper is three-fold: 1) It provides an overview of the most popular ensemble methods, 2) analyzes several fusion schemes using MNIST as guiding thread and 3) introduces MNIST-NET10, a complex heterogeneous fusion architecture based on a degree of certainty aggregation approach; it combines two heterogeneous schemes from the perspective of data, model and fusion strategy. MNIST-NET10 reaches a new record in MNIST with only 10 misclassified images. Our analysis shows that such complex heterogeneous fusion architectures based on the degree of certainty can be considered as a way of taking benefit from diversity.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Knowing the extent and environmental drivers of forests is key to successfully restore degraded ecosystems, and to mitigate climate change and desertification impacts using tree planting. Water ...availability is the main limiting factor for the development of forests in drylands, yet the importance of groundwater resources and palaeoclimate as drivers of their current distribution has been neglected. Here we report that mid-Holocene climates and aquifer trends are key predictors of the distribution of dryland forests worldwide. We also updated the global extent of dryland forests to 1,283 million hectares and showed that failing to consider past climates and aquifers has resulted in ignoring or misplacing up to 130 million hectares of forests in drylands. Our findings highlight the importance of a wetter past and well-preserved aquifers to explain the current distribution of dryland forests, and can guide restoration actions by avoiding unsuitable areas for tree establishment in a drier world.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global ...LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet.
This paper presents TimeSpec4LULC (https://doi.org/10.5281/zenodo.5913554; Khaldi et al., 2022), a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500 m resolution, from 2000 to 2021, and was annotated using spatial–temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE).
The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial–temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8 d temporal granularity into monthly composites; (3) merging Terra + Aqua data into a combined time series; and (4) extracting, at the pixel level, 6 076 531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial–temporal consistency across LULC products, temporal data availability, and the global human modification index.
A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe.
To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery.
This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK