Search

One of the key objectives of the largest government-run Earth Observation missions such as Copernicus Europe, Landsat and similar is to provide reference scientific information to enable monitoring of our changing environment across borders (and beyond visible light!). EO-based products are becoming crucial for spatial planning but also for the econometric assessment of the social benefits, taxation and political decisions in general. We have invited a number of keynote speakers and asked them to share their opinions on the general question “How can Earth Observation (EO) and Machine Learning technology help deliver the green (new) deal and what could potentially be a win-win-win situation?” By win-win-win here we imply: (1) environmental data users (businesses and organizations) win, (2) data producers win, and (3) society wins. Each of the talks was video recorded and is available here. These are the main takeaways., {"references":["Breidenbach, J., Ellison, D., Petersson, H., Korhonen, K. T., Henttonen, H. M., Wallerman, J., … & Næsset, E. (2022). Harvested area did not increase abruptly — how advancements in satellite-based mapping led to erroneous conclusions. Annals of forest science, 79(1), 1–9. https://doi.org/10.1186/s13595-022-01120-4","Ceccherini, G., Duveiller, G., Grassi, G., Lemoine, G., Avitabile, V., Pilli, R., Cescatti, A. (2020). Abrupt increase in harvested forest area over Europe after 2015. Nature 583(7814):72–77. https://doi.org/10.1038/s41586-020-2438-y","Ceccherini, G., Duveiller, G., Grassi, G., Lemoine, G., Avitabile, V., Pilli, R., & Cescatti, A. (2022). Potentials and limitations of NFIs and remote sensing in the assessment of harvest rates: a reply to Breidenbach et al. Annals of Forest Science, 79(1), 1–7. https://doi.org/10.1186/s13595-022-01150-y","Nabuurs, G. J., Harris, N., Sheil, D., Palahi, M., Chirici, G., Boissière, M., … & Valbuena, R. (2022). Glasgow forest declaration needs new modes of data ownership. Nature Climate Change, 12(5), 415–417. https://doi.org/10.1038/s41558-022-01343-3","Sabatini, F. M., Jiménez-Alfaro, B., Jandt, U., Chytrý, M., Field, R., Kessler, M., … & Bruelheide, H. (2022). Global patterns of vascular plant alpha diversity. Nature communications, 13(1), 4683. https://doi.org/10.1038/s41467-022-32063-z","Schramm, M., Pebesma, E., Milenković, M., Foresta, L., Dries, J., Jacob, A., … & Reiche, J. (2021). The openeo api–harmonising the use of earth observation cloud services using virtual data cube functionalities. Remote Sensing, 13(6), 1125. https://doi.org/10.3390/rs13061125","Simoes, R., Camara, G., Queiroz, G., Souza, F., Andrade, P. R., Santos, L., … & Ferreira, K. (2021). Satellite image time series analysis for big earth observation data. Remote Sensing, 13(13), 2428. https://doi.org/10.3390/rs13132428","Venter, Z. S., Barton, D. N., Chakraborty, T., Simensen, T., & Singh, G. (2022). Global 10 m Land Use Land Cover Datasets: A Comparison of Dynamic World, World Cover and Esri Land Cover. Remote Sensing, 14(16), 4101. https://doi.org/10.3390/rs14164101","Wagemann, J., Siemen, S., Seeger, B., & Bendix, J. (2021). Users of open Big Earth data–An analysis of the current state. Computers & Geosciences, 157, 104916. https://doi.org/10.1016/j.cageo.2021.104916"]}

This R tutorial explains step-by-step how to use Ensemble Machine Learning to generate predictions (maps) from 2D, 3D, 2D+T training (point) datasets. We show functionality to do automated benchmarking for spatial/spatiotemporal prediction problems, and for which we use primarily the mlr framework and spatial packages terra, rgdal and similar. In addition, we explain how to plot spatial/spatiotemporal prediction inputs and outputs, including how to do accuracy plots and predictograms. We focus engineering the predictive mapping around three main areas: (a) accuracy performance, (b) computing time, (c) robustness of the algorithms (sensitivity to noise, artifacts etc). Online version of the book is available at: https://opengeohub.github.io/spatial-prediction-eml/, Acknowledgement: CEF Telecom project 2018-EU-IA-0095. This project is co-financed by the by the European Union.

This R tutorial contains instructions on how to organize spatial sampling using R packages. It is organized in three main parts: (1) planning new surveys: i.e. starting from scratch, (2) implementing resampling: learning from existing point data, focusing on subsampling and Cross-Validation strategies, (3) planning additional sampling: sampling additional point data based on initial models, the running re-analysis and gradually improving models until the maximum possible accuracy is reached. We use sample datasets to demonstrate processing steps and provide interpretation and dicussion of the results. More chapters will be added in the future. To use most up-to-date copy please refer to: https://opengeohub.github.io/spatial-sampling-ml/.

Land degradation is a systematic loss of function in terrestrial ecosystems: a serious drop in primary productivity, biomass and biodiversity. This means the land produces less than what it is able to at its natural capacity and even eventually deteriorates completely with little to no production at all. No plants. No animals. No water. Where this occurs extensively enough, it also changes the climate. Since the start of the industrial revolution 150 years ago, land degradation has been continuously accelerating at a frightening pace. But all is not lost! We now understand how land degradation can be reversed by systematic land conservation practices, scaling up of agroecological systems, landscape-scale rehydration and massive planting of grasses, shrubs and forests, by leaning into nature and designing and building resilient ecosystems. But where is the potential for (land) restoration the highest? And how can you get involved and help re-green, re-store and expand resilient terrestrial ecosystems?, Published in: https://opengeohub.medium.com/restoration-culture-what-is-land-degradation-how-to-measure-it-and-what-can-you-do-to-reverse-341e448994da

This is a public compendium of global, regional, national and sub-national soil samples and/or soil profile datasets (points with Observations and Measurements of soil properties and characteristics). Datasets listed here, assuming compatible open license, are afterwards imported into the Global compilation of soil chemical and physical properties and soil classes and eventually used to create a better open soil information across countries. Please feel free to contribute entries. See GitHub repository for more detailed instructions. To see the most up-to-date version of this compendium please visit: https://opengeohub.github.io/SoilSamples/, https://opengeohub.github.io/SoilSamples/

Resulting from the GlobalSoilMap initiative and the Globally-integrated Africa Soil Information Service (AfSIS) project, soil property maps of the world were produced in 2014, following the maps of Sub-Saharan Africa produced in 2013. The two maps were fully compliant with the GlobalSoilMap specifications except for the spatial resolution of 1km. The primary soil data used as input for mapping were from the Africa Soil Profiles (AfSP) database and an early version of the World Soil Information Service (WoSIS) database, both compiled mainly from existing sources in collaboration with various partners in Africa and the world. The maps have more recently been updated to a resolution of 250m upon availability of additional data. These initiatives, using a top-down approach due to lack of budget to actively involve soil institutes worldwide, showed that state of the art baseline products can be developed cost-efficiently based on legacy soil data and can be updated when additional, possibly newly collected, data become available. As a result, several bottom-up initiatives in Africa have started similar work aiming to add value to national soil data holdings of mainly analogue and fragmented nature. In collaboration with ISRIC and facilitated by the global soil information facilities (GSIF), the Soil Research Institute in Ghana compiled and georeferenced data, collected during decades of soil studies applying standard procedures, for over 1000 soil profiles adding to the 400 in the AfSP. A similar successful initiative with the University of Dschang and the International Institute of Tropical Agriculture (IITA) in Cameroon compiled data for 1300 soil profiles, including 500 from the AfSP of which many could be georeferenced more accurately. Each of the countries developed a baseline version of the national SoilGrids, with and without using the global SoilGrids maps as covariate. These collaborative studies are good examples how national and global initiatives can strengthen each other as a feasible way forward to compile sufficient data, at low costs, to produce maps that are nationally and locally accurate, detailed and relevant as well as globally coherent, harmonised and complete. Such hybrid approach requires training of national experts and sufficient computational capacity to locally produce maps at high spatial resolution, i.e. 100m, and also requires global standards and mechanisms for sharing and merging of data and results.

Most practical applications of spatial interpolation ignore that some measurements may be more accurate than others. As a result all measurements are treated equally important, while it is intuitively clear that more accurate measurements should carry more weight than less accurate measurements. Geostatistics provides the tools to perform spatial interpolation using measurements with different accuracy levels. In this short paper we use these tools to explore the sensitivity of interpolated maps to differences in measurement accuracy for a case study on mapping topsoil clay content in Namibia using kriging with external drift (KED). We also compare the kriging variance maps and show how incorporation of different measurement accuracy levels influences estimation of the KED model parameters.

The article reviews main principles of running geo-computations in ecology, as illustrated with case studies from the EcoGRID and FlySafe projects, and emphasizes the advantages of using R computing environment as the most attractive programming/scripting environment. Three case studies (including R code) of interest to ecological applications are described: (a) analysis of GPS trajectory data for two gull-birds species; (b) species distribution mapping in space and time for a bird species (sedge warbler; EcoGRID project); and (c) change detection using time-series of maps. The case studies demonstrate that R , together with its numerous packages for spatial and geostatistical analysis, is a well-suited tool to produce quality outputs (maps, statistical models) of interest in Geo-Ecology. Moreover, due to the recent implementation of the maptools and sp packages, such outputs can be easily exported to popular geographical browsers such as Google Earth and similar. The key computational challenges for Computational Geo-Ecology recognized were: (1) solving the problem of input data quality (filtering techniques), (2) solving the problem of computing with large data sets, (3) improving the over-simplistic statistical models, and (4) producing outputs of increasingly higher level of detail.

The study of islands as model systems has played an important role in the development of evolutionary and ecological theory. The 50th anniversary of MacArthur and Wilson's (December 1963) article, 'An equilibrium theory of insular zoogeography', was a recent milestone for this theme. Since 1963, island systems have provided new insights into the formation of ecological communities. Here, building on such developments, we highlight prospects for research on islands to improve our understanding of the ecology and evolution of communities in general. Throughout, we emphasise how attributes of islands combine to provide unusual research opportunities, the implications of which stretch far beyond islands. Molecular tools and increasing data acquisition now permit re-assessment of some fundamental issues that interested MacArthur and Wilson. These include the formation of ecological networks, species abundance distributions, and the contribution of evolution to community assembly. We also extend our prospects to other fields of ecology and evolution - understanding ecosystem functioning, speciation and diversification - frequently employing assets of oceanic islands in inferring the geographic area within which evolution has occurred, and potential barriers to gene flow. Although island-based theory is continually being enriched, incorporating non-equilibrium dynamics is identified as a major challenge for the future. © 2014 John Wiley & Sons Ltd/CNRS.

The MacArthur and Wilson island biogeography theory relates species diversity on islands as the result of equilibrium between extinctions and colonization events which rates depend on island size and isolation. Although island size and isolation can be considered static on ecological timescales (

Geomorphological maps that are automatically extracted from digital elevation data are gradually replacing classical geomorphological maps. Commonly, digital mapping projects are based upon statistical techniques, object-based protocols or both. In addition to digital elevation data, expert knowledge can still be used to calibrate feature extraction algorithms. Such hybrid expert/statistical-based methods translate land surface parameters into areal extents of geomorphological features in an automated, reproducible manner, which increases spatial detail of final products and speeds up map production. The development of efficient statistical methods for the extraction of geomorphological features is today promoted by high-resolution digital elevation data from light detection and ranging (LiDAR) technology. In this chapter, case studies from the Netherlands (very low relief) and Austrian Alps (high relief) are presented to illustrate how statistical-based and object-based supervised classification can be used for the semi-automated identification and extraction of geomorphological features using high-resolution LiDAR digital elevation models (DEMs). In the first case study, multinomial logistic regression is used to increase the detail of a classic geomorphological map. Medial axes of the manually delineated polygons are used to locate the training pixels and to build the statistical model, which is then implemented over the whole area of interest. In the second case study, object-based segmentation of slope and topographic openness extracted from LiDAR data are used for rule-based mapping of geomorphological features. Both studies confirm that LiDAR DEMs can be used to increase detail of existing geomorphological maps. In addition, semi-automated techniques provide a more objective framework for geomorphological mapping.

Most scientific journals provide guidelines for authors - how to format references and prepare artwork, how many copies of the paper to submit and to which address. However, most official guidelines say little about how you should design and produce your paper and the chances that it will be accepted. This book provides a comprehensive but focused guide to producing scientific information - from research design to publication. It provides practical tips and answers to some of the most frequently asked questions: Why do we publish in the first place? What is OA publishing and why bother about it? What is the h-index? What is a Journal Impact Factor and does it matter? How can I increase my research production efficiency? Why should I use OS software tools for academic work? How can I produce graphics that will impress? How can I brainstorm good titles? How can I select a suitable journal and where can I find out more about it? How can I get into the reviewers' heads? This is an Open Access publication.

Object-Based Image Analysis (OBIA) is considered a useful tool for analyzing high-resolution digital terrain data. In the past, both segmentation and classification parameters were optimized manually by trial and error. We propose a method to automatically optimize classification parameters for increasing the accuracy and efficiency of OBIA for semi-automated geomorphological mapping. We test our method by semi-automatically extracting three geomorphological ‘feature types’ (river terrace, gypsum sink holes, and fluvial incision) from a 1m Digital Terrain Model (DTM) of an alpine area in Vorarlberg, Austria. Segmentation parameters were optimized for each specific geomorphological ‘feature type’, by comparing frequency distribution matrices of training samples and automatically generated image objects. Subsequently image objects are iteratively classified with varying classification settings. The best classification scores and corresponding segmentation and classification settings are summarized in a library of feature signatures for stratified feature extraction. Our results show that through optimization, a limited number of classifiers can be used to accurately classify geomorphological features in complex terrain. This allows classification schemes to be standardized for automated and effective analysis of high-resolution terrain data. In addition, by automating mapping procedures, this research increases the efficiency of geomorphological research. Further research will include the classification of the remaining geomorphological ‘feature types’ to create a full-covered geomorphological map, and the application of the feature signature library to other areas.