Articles | Volume 15, issue 2
https://doi.org/10.5194/essd-15-681-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-15-681-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Data description paper
| 
08 Feb 2023
Data description paper |
| 08 Feb 2023
TreeSatAI Benchmark Archive: a multi-sensor, multi-label dataset for tree species classification in remote sensing
Steve Ahlswede
CORRESPONDING AUTHOR
Remote Sensing Image Analysis Group, Technische Universität Berlin, Einsteinufer 17, 10587 Berlin, Germany
Christian Schulz
CORRESPONDING AUTHOR
Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Straße des 17. Juni 145, 10623 Berlin, Germany
Christiano Gava
Smart Data and Knowledge Services, Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI), Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Patrick Helber
Vision Impulse GmbH, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Benjamin Bischke
Vision Impulse GmbH, Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Michael Förster
Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Straße des 17. Juni 145, 10623 Berlin, Germany
Florencia Arias
Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Straße des 17. Juni 145, 10623 Berlin, Germany
Jörn Hees
Smart Data and Knowledge Services, Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI), Trippstadter Str. 122, 67663 Kaiserslautern, Germany
Fachbereich Informatik, Hochschule Bonn-Rhein-Sieg, Grantham-Allee 20, 53757 Sankt Augustin, Germany
Begüm Demir
Remote Sensing Image Analysis Group, Technische Universität Berlin, Einsteinufer 17, 10587 Berlin, Germany
Birgit Kleinschmit
Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Straße des 17. Juni 145, 10623 Berlin, Germany
Related authors
No articles found.
Maik Heistermann, Till Francke, Lena Scheiffele, Katya Dimitrova Petrova, Christian Budach, Martin Schrön, Benjamin Trost, Daniel Rasche, Andreas Güntner, Veronika Döpper, Michael Förster, Markus Köhli, Lisa Angermann, Nikolaos Antonoglou, Manuela Zude-Sasse, and Sascha Oswald
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2023-19, https://doi.org/10.5194/essd-2023-19, 2023
Revised manuscript under review for ESSD
Short summary
Short summary
Cosmic-ray neutron sensing (CRNS) allows for the non-invasive estimation of root-zone soil water content (SWC). The signal observed by a single CRNS sensor is influenced by the SWC in a radius of around 150 m (the footprint). Here, we have put together a cluster of eight CRNS sensors with overlapping footprints at an agricultural research site in north-east Germany. That way, we hope to represent spatial SWC heterogeneity instead of retrieving just one average SWC estimate from a single sensor.
Alby Duarte Rocha, Stenka Vulova, Christiaan van der Tol, Michael Förster, and Birgit Kleinschmit
Hydrol. Earth Syst. Sci., 26, 1111–1129, https://doi.org/10.5194/hess-26-1111-2022, https://doi.org/10.5194/hess-26-1111-2022, 2022
Short summary
Short summary
Evapotranspiration (ET) is a sum of soil evaporation and plant transpiration. ET produces a cooling effect to mitigate heat waves in urban areas. Our method uses a physical model with remote sensing and meteorological data to predict hourly ET. Designed for uniform vegetation, it overestimated urban ET. To correct it, we create a factor using vegetation fraction that proved efficient for reducing bias and improving accuracy. This approach was tested on two Berlin sites and can be used to map ET.
Lena-Marie Kuhlemann, Doerthe Tetzlaff, Aaron Smith, Birgit Kleinschmit, and Chris Soulsby
Hydrol. Earth Syst. Sci., 25, 927–943, https://doi.org/10.5194/hess-25-927-2021, https://doi.org/10.5194/hess-25-927-2021, 2021
Short summary
Short summary
We studied water partitioning under urban grassland, shrub and trees during a warm and dry growing season in Berlin, Germany. Soil evaporation was highest under grass, but total green water fluxes and turnover time of soil water were greater under trees. Lowest evapotranspiration losses under shrub indicate potential higher drought resilience. Knowledge of water partitioning and requirements of urban green will be essential for better adaptive management of urban water and irrigation strategies.
Benjamin Fersch, Till Francke, Maik Heistermann, Martin Schrön, Veronika Döpper, Jannis Jakobi, Gabriele Baroni, Theresa Blume, Heye Bogena, Christian Budach, Tobias Gränzig, Michael Förster, Andreas Güntner, Harrie-Jan Hendricks Franssen, Mandy Kasner, Markus Köhli, Birgit Kleinschmit, Harald Kunstmann, Amol Patil, Daniel Rasche, Lena Scheiffele, Ulrich Schmidt, Sandra Szulc-Seyfried, Jannis Weimar, Steffen Zacharias, Marek Zreda, Bernd Heber, Ralf Kiese, Vladimir Mares, Hannes Mollenhauer, Ingo Völksch, and Sascha Oswald
Earth Syst. Sci. Data, 12, 2289–2309, https://doi.org/10.5194/essd-12-2289-2020, https://doi.org/10.5194/essd-12-2289-2020, 2020
C. Rumbaur, N. Thevs, M. Disse, M. Ahlheim, A. Brieden, B. Cyffka, D. Duethmann, T. Feike, O. Frör, P. Gärtner, Ü. Halik, J. Hill, M. Hinnenthal, P. Keilholz, B. Kleinschmit, V. Krysanova, M. Kuba, S. Mader, C. Menz, H. Othmanli, S. Pelz, M. Schroeder, T. F. Siew, V. Stender, K. Stahr, F. M. Thomas, M. Welp, M. Wortmann, X. Zhao, X. Chen, T. Jiang, J. Luo, H. Yimit, R. Yu, X. Zhang, and C. Zhao
Earth Syst. Dynam., 6, 83–107, https://doi.org/10.5194/esd-6-83-2015, https://doi.org/10.5194/esd-6-83-2015, 2015
Related subject area
Domain: ESSD – Land | Subject: Land Cover and Land Use
An open-source automatic survey of green roofs in London using segmentation of aerial imagery
Twenty-meter annual paddy rice area map for mainland Southeast Asia using Sentinel-1 synthetic-aperture-radar data
A 29-year time series of annual 300 m resolution plant-functional-type maps for climate models
Estimating local agricultural gross domestic product (AgGDP) across the world
Classification and mapping of European fuels using a hierarchical, multipurpose fuel classification system
Harmonising the land-use flux estimates of global models and national inventories for 2000–2020
Four-century history of land transformation by humans in the United States (1630–2020): annual and 1 km grid data for the HIStory of LAND changes (HISLAND-US)
A 250 m annual alpine grassland AGB dataset over the Qinghai–Tibet Plateau (2000–2019) in China based on in situ measurements, UAV photos, and MODIS data
AsiaRiceYield4km: seasonal rice yield in Asia from 1995 to 2015
UGS-1m: fine-grained urban green space mapping of 31 major cities in China based on the deep learning framework
AI4Boundaries: an open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography
GWL_FCS30: a global 30 m wetland map with a fine classification system using multi-sourced and time-series remote sensing imagery in 2020
CALC-2020: a new baseline land cover map at 10 m resolution for the circumpolar Arctic
MDAS: a new multimodal benchmark dataset for remote sensing
Gridded pollen-based Holocene regional plant cover in temperate and northern subtropical China suitable for climate modelling
Location, biophysical and agronomic parameters for croplands in northern Ghana
Historical nitrogen fertilizer use in China from 1952 to 2018
SiDroForest: a comprehensive forest inventory of Siberian boreal forest investigations including drone-based point clouds, individually labeled trees, synthetically generated tree crowns, and Sentinel-2 labeled image patches
Annual emissions of carbon from land use, land-use change, and forestry 1850–2020
History of anthropogenic Nitrogen inputs (HaNi) to the terrestrial biosphere: a 5 arcmin resolution annual dataset from 1860 to 2019
LUCAS cover photos 2006–2018 over the EU: 874 646 spatially distributed geo-tagged close-up photos with land cover and plant species label
Gridded 5 arcmin datasets for simultaneously farm-size-specific and crop-specific harvested areas in 56 countries
Vectorized dataset of roadside noise barriers in China using street view imagery
A global map of local climate zones to support earth system modelling and urban-scale environmental science
Mapping 10 m global impervious surface area (GISA-10m) using multi-source geospatial data
An improved global land cover mapping in 2015 with 30 m resolution (GLC-2015) based on a multi-source product fusion approach
Charles H. Simpson, Oscar Brousse, Nahid Mohajeri, Michael Davies, and Clare Heaviside
Earth Syst. Sci. Data, 15, 1521–1541, https://doi.org/10.5194/essd-15-1521-2023, https://doi.org/10.5194/essd-15-1521-2023, 2023
Short summary
Short summary
Adding plants to roofs of buildings can reduce indoor and outdoor temperatures and so can reduce urban overheating, which is expected to increase due to climate change and urban growth. To better understand the effect this has on the urban environment, we need data on how many buildings have green roofs already.
We used a computer vision model to find green roofs in aerial imagery in London, producing a dataset identifying what buildings have green roofs and improving on previous methods.
Chunling Sun, Hong Zhang, Lu Xu, Ji Ge, Jingling Jiang, Lijun Zuo, and Chao Wang
Earth Syst. Sci. Data, 15, 1501–1520, https://doi.org/10.5194/essd-15-1501-2023, https://doi.org/10.5194/essd-15-1501-2023, 2023
Short summary
Short summary
Over 90 % of the world’s rice is produced in the Asia–Pacific region. In this study, a rice-mapping method based on Sentinel-1 data for mainland Southeast Asia is proposed. A combination of spatiotemporal features with strong generalization is selected and input into the U-Net model to obtain a 20 m resolution rice area map of mainland Southeast Asia in 2019. The accuracy of the proposed method is 92.20 %. The rice area map is concordant with statistics and other rice area maps.
Kandice L. Harper, Céline Lamarche, Andrew Hartley, Philippe Peylin, Catherine Ottlé, Vladislav Bastrikov, Rodrigo San Martín, Sylvia I. Bohnenstengel, Grit Kirches, Martin Boettcher, Roman Shevchuk, Carsten Brockmann, and Pierre Defourny
Earth Syst. Sci. Data, 15, 1465–1499, https://doi.org/10.5194/essd-15-1465-2023, https://doi.org/10.5194/essd-15-1465-2023, 2023
Short summary
Short summary
We built a spatially explicit annual plant-functional-type (PFT) dataset for 1992–2020 exhibiting intra-class spatial variability in PFT fractional cover at 300 m. For each year, 14 maps of percentage cover are produced: bare soil, water, permanent snow/ice, built, managed grasses, natural grasses, and trees and shrubs, each split into leaf type and seasonality. Model simulations indicate significant differences in simulated carbon, water, and energy fluxes in some regions using this new set.
Yating Ru, Brian Blankespoor, Ulrike Wood-Sichra, Timothy S. Thomas, Liangzhi You, and Erwin Kalvelagen
Earth Syst. Sci. Data, 15, 1357–1387, https://doi.org/10.5194/essd-15-1357-2023, https://doi.org/10.5194/essd-15-1357-2023, 2023
Short summary
Short summary
Economic statistics are frequently produced at an administrative level that lacks detail to examine development patterns and the exposure to natural hazards. This paper disaggregates national and subnational administrative statistics of agricultural GDP into a global dataset at the local level using satellite-derived indicators. As an illustration, the paper estimates that the exposure of areas with extreme drought to agricultural GDP is USD 432 billion, where nearly 1.2 billion people live.
Elena Aragoneses, Mariano García, Michele Salis, Luís M. Ribeiro, and Emilio Chuvieco
Earth Syst. Sci. Data, 15, 1287–1315, https://doi.org/10.5194/essd-15-1287-2023, https://doi.org/10.5194/essd-15-1287-2023, 2023
Short summary
Short summary
We present a new hierarchical fuel classification system with a total of 85 fuels that is useful for preventing fire risk at different spatial scales. Based on this, we developed a European fuel map (1 km resolution) using land cover datasets, biogeographic datasets, and bioclimatic modelling. We validated the map by comparing it to high-resolution data, obtaining high overall accuracy. Finally, we developed a crosswalk for standard fuel models as a first assignment of fuel parameters.
Giacomo Grassi, Clemens Schwingshackl, Thomas Gasser, Richard A. Houghton, Stephen Sitch, Josep G. Canadell, Alessandro Cescatti, Philippe Ciais, Sandro Federici, Pierre Friedlingstein, Werner A. Kurz, Maria J. Sanz Sanchez, Raúl Abad Viñas, Ramdane Alkama, Selma Bultan, Guido Ceccherini, Stefanie Falk, Etsushi Kato, Daniel Kennedy, Jürgen Knauer, Anu Korosuo, Joana Melo, Matthew J. McGrath, Julia E. M. S. Nabel, Benjamin Poulter, Anna A. Romanovskaya, Simone Rossi, Hanqin Tian, Anthony P. Walker, Wenping Yuan, Xu Yue, and Julia Pongratz
Earth Syst. Sci. Data, 15, 1093–1114, https://doi.org/10.5194/essd-15-1093-2023, https://doi.org/10.5194/essd-15-1093-2023, 2023
Short summary
Short summary
Striking differences exist in estimates of land-use CO2 fluxes between the national greenhouse gas inventories and the IPCC assessment reports. These differences hamper an accurate assessment of the collective progress under the Paris Agreement. By implementing an approach that conceptually reconciles land-use CO2 flux from national inventories and the global models used by the IPCC, our study is an important step forward for increasing confidence in land-use CO2 flux estimates.
Xiaoyong Li, Hanqin Tian, Chaoqun Lu, and Shufen Pan
Earth Syst. Sci. Data, 15, 1005–1035, https://doi.org/10.5194/essd-15-1005-2023, https://doi.org/10.5194/essd-15-1005-2023, 2023
Short summary
Short summary
We reconstructed land use and land cover (LULC) history for the conterminous United States during 1630–2020 by integrating multi-source data. The results show the widespread expansion of cropland and urban land and the shrinking of natural vegetation in the past four centuries. Forest planting and regeneration accelerated forest recovery since the 1920s. The datasets can be used to assess the LULC impacts on the ecosystem's carbon, nitrogen, and water cycles.
Huifang Zhang, Zhonggang Tang, Binyao Wang, Hongcheng Kan, Yi Sun, Yu Qin, Baoping Meng, Meng Li, Jianjun Chen, Yanyan Lv, Jianguo Zhang, Shuli Niu, and Shuhua Yi
Earth Syst. Sci. Data, 15, 821–846, https://doi.org/10.5194/essd-15-821-2023, https://doi.org/10.5194/essd-15-821-2023, 2023
Short summary
Short summary
The accuracy of regional grassland aboveground biomass (AGB) is always limited by insufficient ground measurements and large spatial gaps with satellite pixels. This paper used more than 37 000 UAV images as bridges to successfully obtain AGB values matching MODIS pixels. The new AGB estimation model had good robustness, with an average R2 of 0.83 and RMSE of 34.13 g m2. Our new dataset provides important input parameters for understanding the Qinghai–Tibet Plateau during global climate change.
Huaqing Wu, Jing Zhang, Zhao Zhang, Jichong Han, Juan Cao, Liangliang Zhang, Yuchuan Luo, Qinghang Mei, Jialu Xu, and Fulu Tao
Earth Syst. Sci. Data, 15, 791–808, https://doi.org/10.5194/essd-15-791-2023, https://doi.org/10.5194/essd-15-791-2023, 2023
Short summary
Short summary
High-spatiotemporal-resolution rice yield datasets are limited over a large region. We proposed an explicit method to predict rice yield based on machine learning methods and generated a seasonal 4 km resolution rice yield dataset across Asia (AsiaRiceYield4km) for 1995–2015. The seasonal rice yield accuracy of AsiaRiceYield4km is high and much improved compared with previous datasets. AsiaRiceYield4km will fill the current data gap and better support agricultural monitoring systems.
Qian Shi, Mengxi Liu, Andrea Marinoni, and Xiaoping Liu
Earth Syst. Sci. Data, 15, 555–577, https://doi.org/10.5194/essd-15-555-2023, https://doi.org/10.5194/essd-15-555-2023, 2023
Short summary
Short summary
A large-scale and high-resolution urban green space (UGS) product with 1 m of 31 major cities in China (UGS-1m) is generated based on a deep learning framework to provide basic UGS information for relevant UGS research, such as distribution, area, and UGS rate. Moreover, an urban green space dataset (UGSet) with a total of 4454 samples of 512 × 512 in size are also supplied as the benchmark to support model training and algorithm comparison.
Raphaël d'Andrimont, Martin Claverie, Pieter Kempeneers, Davide Muraro, Momchil Yordanov, Devis Peressutti, Matej Batič, and François Waldner
Earth Syst. Sci. Data, 15, 317–329, https://doi.org/10.5194/essd-15-317-2023, https://doi.org/10.5194/essd-15-317-2023, 2023
Short summary
Short summary
AI4boundaries is an open AI-ready data set to map field boundaries with Sentinel-2 and aerial photography provided with harmonised labels covering seven countries and 2.5 M parcels in Europe.
Xiao Zhang, Liangyun Liu, Tingting Zhao, Xidong Chen, Shangrong Lin, Jinqing Wang, Jun Mi, and Wendi Liu
Earth Syst. Sci. Data, 15, 265–293, https://doi.org/10.5194/essd-15-265-2023, https://doi.org/10.5194/essd-15-265-2023, 2023
Short summary
Short summary
An accurate global 30 m wetland dataset that can simultaneously cover inland and coastal zones is lacking. This study proposes a novel method for wetland mapping and generates the first global 30 m wetland map with a fine classification system (GWL_FCS30), including five inland wetland sub-categories (permanent water, swamp, marsh, flooded flat and saline) and three coastal wetland sub-categories (mangrove, salt marsh and tidal flats).
Chong Liu, Xiaoqing Xu, Xuejie Feng, Xiao Cheng, Caixia Liu, and Huabing Huang
Earth Syst. Sci. Data, 15, 133–153, https://doi.org/10.5194/essd-15-133-2023, https://doi.org/10.5194/essd-15-133-2023, 2023
Short summary
Short summary
Rapid Arctic changes are increasingly influencing human society, both locally and globally. Land cover offers a basis for characterizing the terrestrial world, yet spatially detailed information on Arctic land cover is lacking. We employ multi-source data to develop a new land cover map for the circumpolar Arctic. Our product reveals regionally contrasting biome distributions not fully documented in existing studies and thus enhances our understanding of the Arctic’s terrestrial system.
Jingliang Hu, Rong Liu, Danfeng Hong, Andrés Camero, Jing Yao, Mathias Schneider, Franz Kurz, Karl Segl, and Xiao Xiang Zhu
Earth Syst. Sci. Data, 15, 113–131, https://doi.org/10.5194/essd-15-113-2023, https://doi.org/10.5194/essd-15-113-2023, 2023
Short summary
Short summary
Multimodal data fusion is an intuitive strategy to break the limitation of individual data in Earth observation. Here, we present a multimodal data set, named MDAS, consisting of synthetic aperture radar (SAR), multispectral, hyperspectral, digital surface model (DSM), and geographic information system (GIS) data for the city of Augsburg, Germany, along with baseline models for resolution enhancement, spectral unmixing, and land cover classification, three typical remote sensing applications.
Furong Li, Marie-José Gaillard, Xianyong Cao, Ulrike Herzschuh, Shinya Sugita, Jian Ni, Yan Zhao, Chengbang An, Xiaozhong Huang, Yu Li, Hongyan Liu, Aizhi Sun, and Yifeng Yao
Earth Syst. Sci. Data, 15, 95–112, https://doi.org/10.5194/essd-15-95-2023, https://doi.org/10.5194/essd-15-95-2023, 2023
Short summary
Short summary
The objective of this study is present the first gridded and temporally continuous quantitative plant-cover reconstruction for temperate and northern subtropical China over the last 12 millennia. The reconstructions are based on 94 pollen records and include estimates for 27 plant taxa, 10 plant functional types, and 3 land-cover types. The dataset is suitable for palaeoclimate modelling and the evaluation of simulated past vegetation cover and anthropogenic land-cover change from models.
Jose Luis Gómez-Dans, Philip Edward Lewis, Feng Yin, Kofi Asare, Patrick Lamptey, Kenneth Kobina Yedu Aidoo, Dilys Sefakor MacCarthy, Hongyuan Ma, Qingling Wu, Martin Addi, Stephen Aboagye-Ntow, Caroline Edinam Doe, Rahaman Alhassan, Isaac Kankam-Boadu, Jianxi Huang, and Xuecao Li
Earth Syst. Sci. Data, 14, 5387–5410, https://doi.org/10.5194/essd-14-5387-2022, https://doi.org/10.5194/essd-14-5387-2022, 2022
Short summary
Short summary
We provide a data set to support mapping croplands in smallholder landscapes in Ghana. The data set contains information on crop location on three agroecological zones for 2 years, temporal series of measurements of leaf area index and leaf chlorophyll concentration for maize canopies and yield. We demonstrate the use of these data to validate cropland masks, create a maize mask using satellite data and explore the relationship between satellite measurements and yield.
Zhen Yu, Jing Liu, and Giri Kattel
Earth Syst. Sci. Data, 14, 5179–5194, https://doi.org/10.5194/essd-14-5179-2022, https://doi.org/10.5194/essd-14-5179-2022, 2022
Short summary
Short summary
We developed a 5 km annual nitrogen (N) fertilizer use dataset in China, covering the period from 1952 to 2018. We found that previous FAO-data-based N fertilizer products overestimated the N use in low, but underestimated in high, cropland coverage areas in China. The new dataset has improved the spatial distribution and corrected the existing biases, which is beneficial for biogeochemical cycle simulations in China, such as the assessment of greenhouse gas emissions and food production.
Femke van Geffen, Birgit Heim, Frederic Brieger, Rongwei Geng, Iuliia A. Shevtsova, Luise Schulte, Simone M. Stuenzi, Nadine Bernhardt, Elena I. Troeva, Luidmila A. Pestryakova, Evgenii S. Zakharov, Bringfried Pflug, Ulrike Herzschuh, and Stefan Kruse
Earth Syst. Sci. Data, 14, 4967–4994, https://doi.org/10.5194/essd-14-4967-2022, https://doi.org/10.5194/essd-14-4967-2022, 2022
Short summary
Short summary
SiDroForest is an attempt to remedy data scarcity regarding vegetation data in the circumpolar region, whilst providing adjusted and labeled data for machine learning and upscaling practices. SiDroForest contains four datasets that include SfM point clouds, individually labeled trees, synthetic tree crowns and labeled Sentinel-2 patches that provide insights into the vegetation composition and forest structure of two important vegetation transition zones in Siberia, Russia.
Richard A. Houghton and Andrea Castanho
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2022-351, https://doi.org/10.5194/essd-2022-351, 2022
Revised manuscript accepted for ESSD
Short summary
Short summary
The paper updates a previous analysis of carbon emissions (annual and national) from land use, land-use change, and forestry, 1850–2020. It used data from the latest (2020) Forest Resource Assessment from the U.N., incorporated shifting cultivation, and included improvements to the bookkeeping model and recent estimates of emissions from peatlands. Net global emissions declined steadily over the decade 2011–2020 (average 0.96 PgC yr-1), falling below 1.0 PgC yr-1 for the first time in 30 years.
Hanqin Tian, Zihao Bian, Hao Shi, Xiaoyu Qin, Naiqing Pan, Chaoqun Lu, Shufen Pan, Francesco N. Tubiello, Jinfeng Chang, Giulia Conchedda, Junguo Liu, Nathaniel Mueller, Kazuya Nishina, Rongting Xu, Jia Yang, Liangzhi You, and Bowen Zhang
Earth Syst. Sci. Data, 14, 4551–4568, https://doi.org/10.5194/essd-14-4551-2022, https://doi.org/10.5194/essd-14-4551-2022, 2022
Short summary
Short summary
Nitrogen is one of the critical nutrients for growth. Evaluating the change in nitrogen inputs due to human activity is necessary for nutrient management and pollution control. In this study, we generated a historical dataset of nitrogen input to land at the global scale. This dataset consists of nitrogen fertilizer, manure, and atmospheric deposition inputs to cropland, pasture, and rangeland at high resolution from 1860 to 2019.
Raphaël d'Andrimont, Momchil Yordanov, Laura Martinez-Sanchez, Peter Haub, Oliver Buck, Carsten Haub, Beatrice Eiselt, and Marijn van der Velde
Earth Syst. Sci. Data, 14, 4463–4472, https://doi.org/10.5194/essd-14-4463-2022, https://doi.org/10.5194/essd-14-4463-2022, 2022
Short summary
Short summary
Between 2006 and 2018, 875 661 LUCAS cover (i.e. close-up) photos were taken over a systematic sample of the European Union. This geo-located photo dataset has been curated and is being made available along with the surveyed label data, including land cover and plant species.
Han Su, Bárbara Willaarts, Diana Luna-Gonzalez, Maarten S. Krol, and Rick J. Hogeboom
Earth Syst. Sci. Data, 14, 4397–4418, https://doi.org/10.5194/essd-14-4397-2022, https://doi.org/10.5194/essd-14-4397-2022, 2022
Short summary
Short summary
There are over 608 million farms around the world but they are not the same. We developed high spatial resolution maps showing where small and large farms were located and which crops were planted for 56 countries. We checked the reliability and have the confidence to use them for the country level and global studies. Our maps will help more studies to easily measure how agriculture policies, water availability, and climate change affect small and large farms.
Zhen Qian, Min Chen, Yue Yang, Teng Zhong, Fan Zhang, Rui Zhu, Kai Zhang, Zhixin Zhang, Zhuo Sun, Peilong Ma, Guonian Lü, Yu Ye, and Jinyue Yan
Earth Syst. Sci. Data, 14, 4057–4076, https://doi.org/10.5194/essd-14-4057-2022, https://doi.org/10.5194/essd-14-4057-2022, 2022
Short summary
Short summary
Roadside noise barriers (RNBs) are important urban infrastructures to ensure a city is liveable. This study provides the first reliable and nationwide vectorized RNB dataset with street view imagery in China. The generated RNB dataset is evaluated in terms of two aspects, i.e., the detection accuracy and the completeness and positional accuracy. The method is based on a developed geospatial artificial intelligence framework.
Matthias Demuzere, Jonas Kittner, Alberto Martilli, Gerald Mills, Christian Moede, Iain D. Stewart, Jasper van Vliet, and Benjamin Bechtel
Earth Syst. Sci. Data, 14, 3835–3873, https://doi.org/10.5194/essd-14-3835-2022, https://doi.org/10.5194/essd-14-3835-2022, 2022
Short summary
Short summary
Because urban areas are key contributors to climate change but are also susceptible to multiple hazards, one needs spatially detailed information on urban landscapes to support environmental services. This global local climate zone map describes this much-needed intra-urban heterogeneity across the whole surface of the earth in a universal language and can serve as a basic infrastructure to study e.g. environmental hazards, energy demand, and climate adaptation and mitigation solutions.
Xin Huang, Jie Yang, Wenrui Wang, and Zhengrong Liu
Earth Syst. Sci. Data, 14, 3649–3672, https://doi.org/10.5194/essd-14-3649-2022, https://doi.org/10.5194/essd-14-3649-2022, 2022
Short summary
Short summary
Using more than 2.7 million Sentinel images, we proposed a global ISA mapping method and produced the 10-m global ISA dataset (GISA-10m), with overall accuracy exceeding 86 %. The inter-comparison between different global ISA datasets showed the superiority of our results. The ISA distribution at urban and rural was discussed and compared. For the first time, courtesy of the high spatial resolution, the global road ISA was further identified, and its distribution was discussed.
Bingjie Li, Xiaocong Xu, Xiaoping Liu, Qian Shi, Haoming Zhuang, Yaotong Cai, and Da He
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2022-142, https://doi.org/10.5194/essd-2022-142, 2022
Revised manuscript accepted for ESSD
Short summary
Short summary
A global land cover map with fine spatial resolution (e.g., 30 m) is important for climate and environmental studies, food security, biodiversity conservation, carbon cycling, etc. In this study, we developed an improved global land cover map in 2015 with 30 m resolution (GLC-2015) by fusing multiple existing land cover products based on the Dempster-Shafer theory of evidence on the Google Earth Engine platform.
Cited articles
Ahlswede, S., Thekke-Madam, N., Schulz, C., Kleinschmit, B., and Demir, B.:
Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree
Species Classification Based on Explanation Methods, in: IEEE International
Geoscience and Remote Sensing Symposium, 17–22 July 2022, Kuala Lumpur, Malaysia, https://doi.org/10.48550/arXiv.2201.07495, 2022. a
Ansari, M., Homayouni, S., Safari, A., and Niazmardi, S.: A New Convolutional
Kernel Classifier for Hyperspectral Image Classification, IEEE J.
Sel. Top. Appl., 14,
11240–11256, 2021. a
Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., and Nemani,
R.: Deepsat: a learning framework for satellite imagery, in: Proceedings of
the 23rd SIGSPATIAL international conference on advances in geographic
information systems, 3–6 November 2015, Seattle, Washington, USA, 1–10, https://doi.org/10.48550/arXiv.1509.03602, 2015. a
Beck, H. E., Zimmermann, N. E., McVicar, T. R., Vergopolan, N., Berg, A., and
Wood, E. F.: Present and future Köppen-Geiger climate classification maps
at 1-km resolution, Scientific Data, 5, 1–12, 2018. a
Böckmann, T.: Warum sind Betriebsinventuren für die forstliche Praxis
wichtig (Why is two-phase sampling for stratification so important for
forestry enterprises?), Forstarchiv, 87, 31–37, 2016. a
Boser, B. E., Guyon, I. M., and Vapnik, V. N.: A training algorithm for optimal
margin classifiers, in: Proceedings of the fifth annual workshop on
Computational learning theory, 27–29 July 1992, New York, United States, 144–152, https://doi.org/10.1145/130385.130401, 1992. a
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001. a
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H.:
Encoder-decoder with atrous separable convolution for semantic image
segmentation, in: Proceedings of the European conference on computer vision
(ECCV), 8–14 September 2018, Munich, Germany, 801–818, https://doi.org/10.48550/arXiv.1802.02611, 2018. a
Cherrington, E., Flores-Anderson, A., Thapa, R. B., Herndon, K. E., Wahome, A.,
Oduor, P., Mubea, K., Ouko, E., and Hanh, N.: Perspectives on the Future
Application of SAR in Forest and Environmental Monitoring, in: The SAR
handbook: comprehensive methodologies for forest monitoring and biomass
estimation, edited by: Flores-Anderson, A. I., Herndon, K. E., Thapa, R. B.,
and Cherrington, E., chap. 8, NASA, https://doi.org/10.25966/nr2c-s697, 2019. a
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L.: Imagenet: A
large-scale hierarchical image database, in: 2009 IEEE conference on computer
vision and pattern recognition, IEEE, 20–25 June 2009, Miami, Florida, USA, 248–255, https://doi.org/10.1109/CVPR.2009.5206848, 2009. a
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X.,
Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N.:
An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale,
in: International Conference on Learning Representations, 26 April–1 May 2020, Addis Ababa, Ethiopia, https://doi.org/10.48550/arXiv.2010.11929, 2020. a
Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F.,
Hoersch, B., Isola, C., Laberinti, P., Martimort, P., Meygret, A., Spoto, F., Sy, O., Marchese, F., and Bargellini, P.: Sentinel-2:
ESA's optical high-resolution mission for GMES operational services, Remote
Sens. Environ., 120, 25–36, 2012. a
Egli, S. and Höpke, M.: CNN-Based Tree Species Classification Using High
Resolution RGB Image Data from Automated UAV Observations, Remote Sens.,
12, 3892, https://doi.org/10.3390/rs12233892, 2020. a
Everingham, M., Van Gool, L., Williams, C. K., Winn, J., and Zisserman, A.: The
pascal visual object classes (voc) challenge, Int. J.
Comput. Vision, 88, 303–338, 2010. a
Fassnacht, F. E., Latifi, H., Stereńczak, K., Modzelewska, A., Lefsky, M.,
Waser, L. T., Straub, C., and Ghosh, A.: Review of studies on tree species
classification from remotely sensed data, Remote Sens. Environ., 186,
64–87, 2016. a
Fricker, G. A., Ventura, J. D., Wolf, J. A., North, M. P., Davis, F. W., and
Franklin, J.: A Convolutional Neural Network Classifier Identifies Tree
Species in Mixed-Conifer Forest from Hyperspectral Imagery, Remote Sensing,
11, 2326, https://doi.org/10.3390/rs11192326, 2019. a
Ganz, S., Adler, P., and Kändler, G.: Forest Cover Mapping Based on a
Combination of Aerial Images and Sentinel-2 Satellite Data Compared to
National Forest Inventory Data, Forests, 11, 1322, https://doi.org/10.3390/f11121322, 2020. a, b
Goutte, C. and Gaussier, E.: A probabilistic interpretation of precision,
recall and F-score, with implication for evaluation, in: Advances in
Information Retrieval. Lecture Notes in Computer Science, Vol. 3408, edited by: Losada,
D. E. and Fernández-Luna, J. M., Springer, 345–359, https://doi.org/10.1007/978-3-540-31865-1_25, 2005. a
Grabska, E., Hostert, P., Pflugmacher, D., and Ostapowicz, K.: Forest stand
species mapping using the Sentinel-2 time series, Remote Sens., 11, 1197, https://doi.org/10.3390/rs11101197,
2019. a, b
Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C.,
Turakhia, M. P., and Ng, A. Y.: Cardiologist-level arrhythmia detection and
classification in ambulatory electrocardiograms using a deep neural network,
Nat. Med., 25, 65–69, 2019. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image
recognition, in: Proceedings of the IEEE conference on computer vision and
pattern recognition, 27–30 June 2016, Las Vegas, Nevada, USA, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016. a
Helber, P., Bischke, B., Dengel, A., and Borth, D.: EuroSAT: A Novel Dataset
and Deep Learning Benchmark for Land Use and Land Cover Classification, IEEE
J. Sel. Top. Appl.,
12, 2217–2226, 2019. a
Hemmerling, J., Pflugmacher, D., and Hostert, P.: Mapping temperate forest tree
species using dense Sentinel-2 time series, Remote Sens. Environ.,
267, 112743, https://doi.org/10.1016/j.rse.2021.112743, 2021. a
Hlásny, T., Barka, I., Roessiger, J., Kulla, L., Trombik, J.,
Sarvašová, Z., Bucha, T., Kovalčík, M., and
Čihák, T.: Conversion of Norway spruce forests in the face of
climate change: a case study in Central Europe, Eur. J. For.
Res., 136, 1013–1028, 2017. a
Hollaus, M. and Vreugdenhil, M.: Radar satellite imagery for detecting bark
beetle outbreaks in forests, Current Forestry Reports, 5, 240–250, 2019. a
Holzwarth, S., Thonfeld, F., Abdullahi, S., Asam, S., Da Ponte Canova, E.,
Gessner, U., Huth, J., Kraus, T., Leutner, B., and Kuenzer, C.: Earth
observation based monitoring of forests in Germany: A review, Remote Sens.,
12, 3570, https://doi.org/10.3390/rs12213570, 2020. a, b, c, d
Hong, D., Gao, L., Yokoya, N., Yao, J., Chanussot, J., Du, Q., and Zhang, B.:
More diverse means better: Multimodal deep learning meets remote-sensing
imagery classification, IEEE T. Geosci. Remote Sens.,
59, 4340–4354, 2020. a
Immitzer, M., Neuwirth, M., Böck, S., Brenner, H., Vuolo, F., and
Atzberger, C.: Optimal input features for tree species classification in
Central Europe based on multi-temporal Sentinel-2 data, Remote Sens., 11,
2599, https://doi.org/10.3390/rs11222599, 2019. a, b
IPCC: Climate Change 2014: Synthesis Report. Contribution of Working Groups I,
II and III to the Fifth Assessment Report of the Intergovernmental Panel on
Climate Change, IPCC, Geneva, Switzerland, https://www.ipcc.ch/report/ar5/syr/ (last access: 31 January 2023), 2014. a
Karlson, M., Ostwald, M., Reese, H., Sanou, J., Tankoano, B., and Mattsson, E.:
Mapping tree canopy cover and aboveground biomass in Sudano-Sahelian
woodlands using Landsat 8 and random forest, Remote Sens., 7,
10017–10041, 2015. a
Kattenborn, T., Eichel, J., Wiser, S., Burrows, L., Fassnacht, F. E., and
Schmidtlein, S.: Convolutional Neural Networks accurately predict cover
fractions of plant species and communities in Unmanned Aerial Vehicle
imagery, Remote Sensing in Ecology and Conservation, 6, 472–486, 2020. a
Kattenborn, T., Leitloff, J., Schiefer, F., and Hinz, S.: Review on
Convolutional Neural Networks (CNN) in vegetation remote sensing, ISPRS
J. Photogramm., 173, 24–49, 2021. a
Kowalski, K., Senf, C., Hostert, P., and Pflugmacher, D.: Characterizing spring
phenology of temperate broadleaf forests using Landsat and Sentinel-2 time
series, Int. J. Appl. Earth Obs., 92, 102172, https://doi.org/10.1016/j.jag.2020.102172, 2020. a, b
Krzystek, P., Serebryanyk, A., Schnörr, C., Červenka, J., and
Heurich, M.: Large-Scale Mapping of Tree Species and Dead Trees in
Šumava National Park and Bavarian Forest National Park Using Lidar and
Multispectral Imagery, Remote Sensing, 12, 661, https://doi.org/10.3390/rs12040661, 2020. a
LGLN: Geodatenportal Niedersachsen (GDI-NI), Landesamt für Geoinformation und
Landesvermessung Niedersachsen,
https://www.geodaten.niedersachsen.de/, last access: 31 December 2020. a
MacDicken, K., Jonsson, Ö., Piña, L., Maulo, S., Contessa, V., Adikari,
Y., Garzuglia, M., Lindquist, E., Reams, G., and D'Annunzio, R.: Global
forest resources assessment 2015: how are the world's forests changing?, FAO, https://agris.fao.org/agris-search/search.do?recordID=XF2017001127 (last access: 31 January 2023),
2016. a
Martins, G. B., La Rosa, L. E. C., Happ, P. N., Coelho Filho, L. C. T., Santos,
C. J. F., Feitosa, R. Q., and Ferreira, M. P.: Deep learning-based tree
species mapping in a highly diverse tropical urban setting, Urban For. Urban Gree., 64, 127241, https://doi.org/10.1016/j.ufug.2021.127241, 2021. a
Mäyrä, J., Keski-Saari, S., Kivinen, S., Tanhuanpää, T.,
Hurskainen, P., Kullberg, P., Poikolainen, L., Viinikka, A., Tuominen, S.,
Kumpula, T., and Vihervaara, P.: Tree species classification from airborne hyperspectral
and LiDAR data using 3D convolutional neural networks, Remote Sens.
Environ., 256, 112322, https://doi.org/10.1016/j.rse.2021.112322, 2021. a
NW-FVA: Waldzustandsbericht 2021 für Niedersachsen, Nordwestdeutsche
Forstliche Versuchsanstalt, Niedersächsisches Ministerium für
Ernährung, Landwirtschaft und Verbraucherschutz, Zenodo,
https://doi.org/10.5281/zenodo.5615008, 2021. a
Ottosen, T.-B., Petch, G., Hanson, M., and Skjøth, C. A.: Tree cover mapping
based on Sentinel-2 images demonstrate high thematic accuracy in Europe,
Int. J. Appl. Earth Obs., 84,
101947, https://doi.org/10.1016/j.jag.2019.101947, 2020. a
Pasquarella, V. J., Holden, C. E., and Woodcock, C. E.: Improved mapping of
forest type using spectral-temporal Landsat features, Remote Sens.
Environ., 210, 193–207, 2018. a
Saborowski, J., Marx, A., Nagel, J., and Böckmann, T.: Double sampling for
stratification in periodic inventories—Infinite population approach, Forest
Ecol. Manag., 260, 1886–1895, 2010. a
Schmitt, M., Hughes, L. H., Qiu, C., and Zhu, X. X.: SEN12MS–A Curated Dataset
of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and
Data Fusion, arXiv [preprint], https://doi.org/10.48550/arXiv.1906.07789, 2019. a
Schuldt, B., Buras, A., Arend, M., Vitasse, Y., Beierkuhnlein, C., Damm, A.,
Gharun, M., Grams, T. E., Hauck, M., Hajek, P., Hartmann, H., Hiltbrunner, E., Hoch, G., Holloway-Phillips, M., Körner, C., Larysch, E., Lübbe, T., Nelson, D., Rammig, A., Rigling, A., Rose, L., Ruehr, N., Schumann, K., Weiser, F., Werner, C., Wohlgemuth, T., Zang, C., and Kahmen, A.: A first assessment of
the impact of the extreme 2018 summer drought on Central European forests,
Basic Appl. Ecol., 45, 86–103, 2020. a
Scott, G. J., England, M. R., Starms, W. A., Marcum, R. A., and Davis, C. H.:
Training deep convolutional neural networks for land–cover classification of
high-resolution imagery, IEEE Geosci. Remote S., 14,
549–553, 2017. a
Senf, C., Buras, A., Zang, C. S., Rammig, A., and Seidl, R.: Excess forest
mortality is consistently linked to drought across Europe, Nat.
Commun., 11, 1–8, 2020. a
Sesnie, S. E., Finegan, B., Gessler, P. E., Thessler, S., Ramos Bendana, Z.,
and Smith, A. M.: The multispectral separability of Costa Rican rainforest
types with support vector machines and Random Forest decision trees,
Int. J. Remote Sens., 31, 2885–2909, 2010. a
Smith, L. N.: Cyclical learning rates for training neural networks, in: 2017
IEEE winter conference on applications of computer vision (WACV), IEEE, 24–31 March 2017, Santa Rosa, CA, USA,
464–472, https://doi.org/10.1109/WACV.2017.58, 2017. a
Sumbul, G., Charfuelan, M., Demir, B., and Markl, V.: Bigearthnet: A
Large-Scale Benchmark Archive for Remote Sensing Image Understanding, in:
IEEE International Geoscience and Remote Sensing Symposium, 28 July–2 August 2019, Yokohama, Japan, 5901–5904, https://doi.org/10.1109/IGARSS.2019.8900532,
2019. a, b
Sumbul, G., De Wall, A., Kreuziger, T., Marcelino, F., Costa, H., Benevides,
P., Caetano, M., Demir, B., and Markl, V.: BigEarthNet-MM: A Large-Scale,
Multimodal, Multilabel Benchmark Archive for Remote Sensing Image
Classification and Retrieval, IEEE Geoscience and Remote Sensing Magazine, 9,
174–180, 2021. a
Takahashi, K., Yamamoto, K., Kuchiba, A., and Koyama, T.: Confidence interval
for micro-averaged F1 and macro-averaged F1 scores, Appl. Intell., 52,
4961–4972, 2022. a
Tanase, M. A., Aponte, C., Mermoz, S., Bouvet, A., Le Toan, T., and Heurich,
M.: Detection of windthrows and insect outbreaks by L-band SAR: A case study
in the Bavarian Forest National Park, Remote Sens. Environ., 209,
700–711, 2018. a
Thonfeld, F., Gessner, U., Holzwarth, S., Kriese, J., da Ponte, E., Huth, J.,
and Kuenzer, C.: A First Assessment of Canopy Cover Loss in Germany's
Forests after the 2018–2020 Drought Years, Remote Sens., 14, 562, https://doi.org/10.3390/rs14030562, 2022. a
Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E.,
Potin, P., Rommen, B., Floury, N., Brown, M., Traver, I. N., Deghaye, P., Duesmann, B., Rosich, B., Miranda, N., Bruno, C., L'Abbate, M., Croci, R., Pietropaolo, A., Huchler, M., and Rostan, F.: GMES Sentinel-1
mission, Remote Sens. Environ., 120, 9–24, 2012. a
Tucker, C. J.: Red and photographic infrared linear combinations for monitoring
vegetation, Remote Sens. Environ., 8, 127–150, 1979. a
Waser, L. T., Rüetschi, M., Psomas, A., Small, D., and Rehush, N.: Mapping
dominant leaf type based on combined Sentinel-1/-2 data–Challenges for
mountainous countries, ISPRS J. Photogramm.,
180, 209–226, 2021. a
Weinstein, B. G., Marconi, S., Bohlman, S., Zare, A., and White, E.: Individual
tree-crown detection in RGB imagery using semi-supervised deep learning
neural networks, Remote Sensing, 11, 1309, https://doi.org/10.3390/rs11111309, 2019a. a, b
Weinstein, B. G., Marconi, S., Bohlman, S. A., Zare, A., and White, E. P.:
Geographic generalization in airborne RGB deep learning tree detection,
bioRxiv [preprint], https://doi.org/10.1101/790071, 2019b. a
Weinstein, B. G., Marconi, S., Bohlman, S., Zare, A., Singh, A., Graves, S. J.,
and White, E.: A remote sensing derived data set of 100 million individual tree crowns for the National Ecological Observatory Network,
eLife, 10, e62922, https://doi.org/10.7554/eLife.62922, 2021. a, b
Welle, T., Aschenbrenner, L., Kuonath, K., Kirmaier, S., and Franke, J.:
Mapping Dominant Tree Species of German Forests, Remote Sens., 14, 3330, https://doi.org/10.3390/rs14143330,
2022. a
Wurm, M., Stark, T., Zhu, X. X., Weigand, M., and Taubenböck, H.: Semantic
segmentation of slums in satellite images using transfer learning on fully
convolutional neural networks, ISPRS J. Photogramm., 150, 59–69, 2019. a
Xu, K., Zhang, Z., Yu, W., Zhao, P., Yue, J., Deng, Y., and Geng, J.: How
Spatial Resolution Affects Forest Phenology and Tree-Species Classification
Based on Satellite and Up-Scaled Time-Series Images, Remote Sens., 13,
2716, https://doi.org/10.3390/rs13142716, 2021. a
Yang, Y. and Newsam, S.: Bag-Of-Visual-Words and Spatial Extensions for
Land-Use Classification, ACM SIGSPATIAL International Conference on Advances
in Geographic Information Systems, 2–5 November 2005, San Jose, California, USA, https://doi.org/10.1145/1869790.1869829, 2010.
a
Zhang, C., Xia, K., Feng, H., Yang, Y., and Du, X.: Tree species classification
using deep learning and RGB optical images obtained by an unmanned aerial
vehicle, J. Forestry Res., 32, 1879–1888, 2021. a
Short summary
Imagery from air and space is the primary source of large-scale forest mapping. Our study introduces a new dataset with over 50000 image patches prepared for deep learning tasks. We show how the information for 20 European tree species can be extracted from different remote sensing sensors. Our algorithms can detect single species with precision scores up to 88 %. With a pixel size of 20×20 cm, forestry administration can now derive large-scale tree species maps at a very high resolution.
Imagery from air and space is the primary source of large-scale forest mapping. Our study...
