diff --git a/joss.06692/10.21105.joss.06692.crossref.xml b/joss.06692/10.21105.joss.06692.crossref.xml new file mode 100644 index 0000000000..265f624f0c --- /dev/null +++ b/joss.06692/10.21105.joss.06692.crossref.xml @@ -0,0 +1,316 @@ + + + + 20240716213927-953416e8ef1c8d4dec03f013a8fadf19af2971b6 + 20240716213927 + + JOSS Admin + admin@theoj.org + + The Open Journal + + + + + Journal of Open Source Software + JOSS + 2475-9066 + + 10.21105/joss + https://joss.theoj.org + + + + + 07 + 2024 + + + 9 + + 99 + + + + scikit-eo: A Python package for Remote Sensing Data +Analysis + + + + Yonatan + Tarazona + https://orcid.org/0000-0002-5208-1004 + + + Fernando + Benitez-Paez + https://orcid.org/0000-0002-9884-6471 + + + Jakub + Nowosad + https://orcid.org/0000-0002-1057-3721 + + + Fabian + Drenkhan + https://orcid.org/0000-0002-9443-9596 + + + Martín E. + Timaná + https://orcid.org/0000-0003-1559-4449 + + + + 07 + 16 + 2024 + + + 6692 + + + 10.21105/joss.06692 + + + http://creativecommons.org/licenses/by/4.0/ + http://creativecommons.org/licenses/by/4.0/ + http://creativecommons.org/licenses/by/4.0/ + + + + Software archive + 10.5281/zenodo.12688708 + + + GitHub review issue + https://github.com/openjournals/joss-reviews/issues/6692 + + + + 10.21105/joss.06692 + https://joss.theoj.org/papers/10.21105/joss.06692 + + + https://joss.theoj.org/papers/10.21105/joss.06692.pdf + + + + + + Fusing Landsat and SAR data for mapping +tropical deforestation through machine learning classification and the +PVts-β non-seasonal detection approach + Tarazona + Canadian Journal of Remote +Sensing + 47 + 10.1080/07038992.2021.1941823 + 2021 + Tarazona, Y., Alaitz, Z., Xavier, P., +Antoni, B., Jakub, N., & Hamdi A., Z. (2021). Fusing Landsat and SAR +data for mapping tropical deforestation through machine learning +classification and the PVts-β non-seasonal detection approach. Canadian +Journal of Remote Sensing, 47, 677–696. +https://doi.org/10.1080/07038992.2021.1941823 + + + Monitoring tropical forest degradation using +remote sensing. Challenges and opportunities in the Madre de Dios +region, Peru + Tarazona + Remote Sensing Applications: Society and +Environment + 19 + 10.1016/j.rsase.2020.100337 + 2352-9385 + 2020 + Tarazona, Y., & Miyasiro-López, +M. (2020). Monitoring tropical forest degradation using remote sensing. +Challenges and opportunities in the Madre de Dios region, Peru. Remote +Sensing Applications: Society and Environment, 19, 100337. +https://doi.org/10.1016/j.rsase.2020.100337 + + + Improving tropical deforestation detection +through using photosynthetic vegetation time series – +(PVts-β) + Tarazona + Ecological Indicators + 94 + 10.1016/j.ecolind.2018.07.012 + 1470-160X + 2018 + Tarazona, Y., Mantas, V. M., & +Pereira, A. J. S. C. (2018). Improving tropical deforestation detection +through using photosynthetic vegetation time series – (PVts-β). +Ecological Indicators, 94, 367–379. +https://doi.org/10.1016/j.ecolind.2018.07.012 + + + Good practices for estimating area and +assessing accuracy of land change + Olofsson + Remote Sensing of Environment + 148 + 10.1016/j.rse.2014.02.015 + 0034-4257 + 2014 + Olofsson, P., Foody, G. M., Herold, +M., Stehman, S. V., Woodcock, C. E., & Wulder, M. A. (2014). Good +practices for estimating area and assessing accuracy of land change. +Remote Sensing of Environment, 148, 42–57. +https://doi.org/10.1016/j.rse.2014.02.015 + + + Satellite-based data fusion crop type +classification and mapping in Rio Grande do Sul, Brazil + Pott + ISPRS Journal of Photogrammetry and Remote +Sensing + 176 + 10.1016/j.isprsjprs.2021.04.015 + 0924-2716 + 2021 + Pott, L. P., Amado, T. J. C., +Schwalbert, R. A., Corassa, G. M., & Ciampitti, I. A. (2021). +Satellite-based data fusion crop type classification and mapping in Rio +Grande do Sul, Brazil. ISPRS Journal of Photogrammetry and Remote +Sensing, 176, 196–210. +https://doi.org/10.1016/j.isprsjprs.2021.04.015 + + + Recent applications of Landsat 8/OLI and +Sentinel-2/MSI for land use and land cover mapping: A systematic +review + Chaves + Remote Sensing + 18 + 12 + 10.3390/rs12183062 + 2072-4292 + 2020 + Chaves, M. E. D., Picoli, M. C. A., +& Sanches, I. D. (2020). Recent applications of Landsat 8/OLI and +Sentinel-2/MSI for land use and land cover mapping: A systematic review. +Remote Sensing, 12(18). +https://doi.org/10.3390/rs12183062 + + + Assessing environmental impacts of urban +growth using remote sensing + Trinder + Geo-spatial Information +Science + 23 + 10.1080/10095020.2019.1710438 + 2020 + Trinder, J., & Liu, Q. (2020). +Assessing environmental impacts of urban growth using remote sensing. +Geo-Spatial Information Science, 23, 20–39. +https://doi.org/10.1080/10095020.2019.1710438 + + + The role of satellite remote sensing in +climate change studies + Yang + Nature Climate Change + 3 + 10.1038/nclimate1908 + 1758-6798 + 2013 + Yang, J., Gong, P., Fu, R., Zhang, +M., Chen, J., Liang, S., Xu, B., Shi, J., & Dickinson, R. (2013). +The role of satellite remote sensing in climate change studies. Nature +Climate Change, 3, 875–883. +https://doi.org/10.1038/nclimate1908 + + + Integrating remote sensing with ecology and +evolution to advance biodiversity conservation + Cavender-Bares + Nature Ecology & Evolution 2022 +6:5 + 6 + 10.1038/s41559-022-01702-5 + 2397-334X + 2022 + Cavender-Bares, J., Schneider, F. D., +Santos, M. J., Armstrong, A., Carnaval, A., Dahlin, K. M., Fatoyinbo, +L., Hurtt, G. C., Schimel, D., Townsend, P. A., Ustin, S. L., Wang, Z., +& Wilson, A. M. (2022). Integrating remote sensing with ecology and +evolution to advance biodiversity conservation. Nature Ecology & +Evolution 2022 6:5, 6, 506–519. +https://doi.org/10.1038/s41559-022-01702-5 + + + Remote sensing of natural hazard-related +disasters with small drones: Global trends, biases, and research +opportunities + Kucharczyk + Remote Sensing of Environment + 264 + 10.1016/J.RSE.2021.112577 + 0034-4257 + 2021 + Kucharczyk, M., & Hugenholtz, C. +H. (2021). Remote sensing of natural hazard-related disasters with small +drones: Global trends, biases, and research opportunities. Remote +Sensing of Environment, 264, 112577. +https://doi.org/10.1016/J.RSE.2021.112577 + + + The Turing Way: A handbook for reproducible +data science + The Turing Way Community + 10.5281/ZENODO.3233986 + 2019 + The Turing Way Community, Arnold, B., +Bowler, L., Gibson, S., Herterich, P., Higman, R., Krystalli, A., +Morley, A., O’Reilly, M., & Whitaker, K. (2019). The Turing Way: A +handbook for reproducible data science. +https://doi.org/10.5281/ZENODO.3233986 + + + Global-scale hydrological response to future +glacier mass loss + Huss + Nature Climate Change + 8 + 10.1038/s41558-017-0049-x + 2018 + Huss, M., & Hock, R. (2018). +Global-scale hydrological response to future glacier mass loss. Nature +Climate Change, 8, 135–140. +https://doi.org/10.1038/s41558-017-0049-x + + + Accelerated global glacier mass loss in the +early twenty-first century + Hugonnet + Nature + 592 + 10.1038/s41586-021-03436-z + 2018 + Hugonnet, R., McNabb, R., Berthier, +E., Menounos, B., Nuth, C., Girod, L., Farinotti, D., Huss, M., +Dussaillant, I., Brun, F., & Kääb, A. (2018). Accelerated global +glacier mass loss in the early twenty-first century. Nature, 592, +726–731. +https://doi.org/10.1038/s41586-021-03436-z + + + + + + diff --git a/joss.06692/10.21105.joss.06692.pdf b/joss.06692/10.21105.joss.06692.pdf new file mode 100644 index 0000000000..777b3014cc Binary files /dev/null and b/joss.06692/10.21105.joss.06692.pdf differ diff --git a/joss.06692/paper.jats/10.21105.joss.06692.jats b/joss.06692/paper.jats/10.21105.joss.06692.jats new file mode 100644 index 0000000000..ecb59fc4e5 --- /dev/null +++ b/joss.06692/paper.jats/10.21105.joss.06692.jats @@ -0,0 +1,770 @@ + + +
+ + + + +Journal of Open Source Software +JOSS + +2475-9066 + +Open Journals + + + +6692 +10.21105/joss.06692 + +scikit-eo: A Python package for Remote Sensing Data +Analysis + + + +https://orcid.org/0000-0002-5208-1004 + +Tarazona +Yonatan + + + + +https://orcid.org/0000-0002-9884-6471 + +Benitez-Paez +Fernando + + + + +https://orcid.org/0000-0002-1057-3721 + +Nowosad +Jakub + + + + +https://orcid.org/0000-0002-9443-9596 + +Drenkhan +Fabian + + + + +https://orcid.org/0000-0003-1559-4449 + +Timaná +Martín E. + + + + + +Department of Earth Sciences, Center for Earth and Space +Research (CITEUC), University of Coimbra, Portugal + + + + +The School of Geography and Sustainable Development, +University of St Andrews, The UK + + + + +Adam Mickiewicz University in Poznań + + + + +Geography and the Environment, Department of Humanities, +Pontificia Universidad Católica del Perú, Lima, Peru + + + + +Applied Geography Research Center, Pontificia Universidad +Católica del Perú, Lima, Peru + + + + +29 +3 +2024 + +9 +99 +6692 + +Authors of papers retain copyright and release the +work under a Creative Commons Attribution 4.0 International License (CC +BY 4.0) +2022 +The article authors + +Authors of papers retain copyright and release the work under +a Creative Commons Attribution 4.0 International License (CC BY +4.0) + + + +Python +Remote Sensing +Earth Observation +Machine Learning +Deep Learning +Spatial Analysis + + + + + + Summary +

In recent years, a growing body of space-borne and drone imagery + has become available with increasing spatial and temporal resolutions. + This remotely sensed data has enabled researchers to address and + tackle a broader range of challenges effectively by using novel tools + and data. However, analysts spend an important amount of time finding + the adequate libraries to read and process remotely sensed data.

+

With an increasing amount of open access data, there is a growing + need to account for effective open source tools to read, process and + execute analysis that contributes to underpin patterns, changes and + trends that are critical for environmental studies. Applications that + integrate spatial-temporal data are used to study a variety of complex + environmental processes, such as monitoring and assessment of land + cover changes + (Chaves + et al., 2020), crop classifications + (Pott + et al., 2021), deforestation + (Tarazona + et al., 2018), impact on urbanization level + (Trinder + & Liu, 2020) and climate change impacts + (Yang + et al., 2013). Other complex environmental processes that are + monitored by integrating spatial-temporal data are assessments of + glacier retreat + (Hugonnet + et al., 2018), related hydrological change + (Huss + & Hock, 2018), biodiversity conservation + (Cavender-Bares + et al., 2022) and disaster management + (Kucharczyk + & Hugenholtz, 2021).

+

To bridge the gaps in remotely sensed data processing tools, we + here introduce scikit-eo, a brand-new Python package for + satellite remote sensing analysis. Unlike other tools, it is a + centralized, scalable, and open-source toolkit due to its flexibility + in being adapted into large dataset processing pipelines. It provides + central access to the most commonly used Python functions in remote + sensing analysis for environmental studies, including machine learning + methods. scikit-eo stands out with its ability to be used + in various settings, from a lecturer room to a crucial part of any + Python environment in a research project. The majority of the tools + included in scikit-eo are derived from peer-reviewed + scientific publications, ensuring their reliability and accuracy.

+

By integrating this diverse set of tools, scikit-eo + allows to focus on analyzing the results of data rather than being + bogged down by complex lines of code. With its centralized structure, + integrated use cases, and example data, scikit-eo + empowers to optimize resources and dedicate more attention to the + meaningful interpretation of findings in a more efficient way.

+ + + Statement of Need +

As remote sensing data and sophisticated processing tools become + increasingly available, there is a growing need for scalable and + customized toolkits to help environmental researchers classify + satellite and drone imagery quickly and accurately. Our goal is to + simplify the identification of patterns, changes, and trends that are + crucial for environmental research and analysis.

+

In this paper, we introduce scikit-eo, a specialized + library with tailored analysis capabilities designed to meet the + unique demands of environmental studies. From statistical methods to + machine learning algorithms, scikit-eo assists + researchers in uncovering intricate spatial patterns, relationships, + and trends, while also simplifying the evaluation and calibration of + generated outputs.

+ +

Workflow of main functionalities of the + scikit-eo python package as well as outputs that + can be obtained by using the tools developed. +

+ + +

scikit-eo is an open-source package built entirely in + Python through Object-Oriented Programming and Structured Programming + that provides a helpful variety of remote sensing tools (see + [fig:workflow]), + from primary and exploratory functions to more advanced methods to + classify, calibrate, or fuse satellite imagery. Depending on the + users’ needs, scikit-eo can provide the basic but + essential land cover characterization mapping, including the confusion + matrix and the required metrics such as user’s accuracy, producer’s + accuracy, omission and commission errors. These required metrics can + be combined as a pandas DataFrame object. + Furthermore, a class prediction map is a result of land cover mapping, + i.e., a land cover map, which represents the output of the + classification algorithm or the output of the segmentation algorithm. + These two outcomes must include uncertainties with a confidence level + (e.g., at + + 95% + or + + 90%). + All required metrics from the confusion matrix can be easily computed + and included confidence levels with scikit-eo following + guidance proposed by Olofsson et al. + (2014). + Other useful tools for remote sensing analysis can be found in this + package; and for more information about the full list of the supported + functions, tutorials as well as how to install and execute the package + within a Python setting, visit the + scikit-eo + website.

+ + + Audience +

scikit-eo is an adaptable Python package that covers + multiple users, including students, remote sensing professionals, + environmental analysis researchers, and organizations looking for + satellite image analysis. Its tools and algorithms implemented make it + well-suited for various applications, such as university teaching, + that includes technical and practical sessions and cutting-edge + research using the most recent machine learning and deep learning + techniques applied to remote sensing.

+

This python package provides key tools for both students seeking + insights from a satellite image analysis or an experienced researcher + looking for advanced tools. scikit-eo offers a valuable + resource to support the most valuable methods for environmental + studies.

+ + <bold>scikit-eo</bold> as a research tool: +

In environmental studies, particularly in land cover + classification, the availability of scalable but user-friendly + software tools is crucial for facilitating research, analysis, and + modelling. With the widespread adoption of Python as one of the most + popular programming languages, particularly in the GIScience and + remote sensing fields, developing specialized packages has massively + enhanced the effectiveness of environmental research. + scikit-eo is a dedicated piece of software tailored to + address unique challenges encountered in land cover mapping, forest + or land degradation + (Tarazona + & Miyasiro-López, 2020), and the fusion of multiple + satellite imagery from several formats + (Tarazona + et al., 2021). scikit-eo provides the assessment + and calibration metrics to evaluate the provided outputs. The + current version scikit-eo requires that users provide + the dataset to process. However, we expect to provide a wide range + of functionalities for acquiring environmental data from diverse + sources and file formats, enabling researchers to access satellite + imagery.

+

One of scikit-eo’s key strengths is its advanced + analysis capabilities. It provides a rich suite of algorithms + specifically designed for environmental studies, including + statistical analysis, deep learning, data fusion, and spatial + analysis. Researchers can leverage these tools to explore patterns, + relationships, and trends within their datasets, uncover complex + land or forest degradation or mapping, classify the land cover, and + generate insightful visualizations.

+

As a particular example of these advanced analysis capabilities, + we have integrated the + deepLearning function, which + includes the Fully connected layers (FC), also + known as dense layers model. This is one of the + most straightforward yet functional neural networks we can apply to + remote sensing analysis. The term “fully connected” comes from the + fact that each neuron in one layer is connected to every neuron in + the preceding layer, creating a highly interconnected network known + as the Multi-Layer Perceptron (MLP). The model is trained using a + specified dataset, with the bands as input_shape, + including input features and corresponding class labels. The weights + W are initialized and then adjusted during training + to ensure the neural network’s output is consistent with the class + labels. The training process involves minimizing the error function + using Gradient Descent and + backpropagation algorithms. The activation + functions used in this model are ReLU (Rectified Linear + Unit) for the neurons in each hidden layer and + Softmax for the final classification layer. For + more details, see tutorial No + 11 + In future version, u-net architectures will be implemented within + scikit-eo.

+

It’s important to note that ReLU introduces + non-linearity to the model, enabling it to learn complex patterns, + while Softmax is used for multi-class + classification, transforming the output into a probability + distribution over multiple classes and better suited for more than + two land covers. Unlike traditional machine learning models, such as + support vector machine or decision tree, which typically are simpler + and don’t involve multiple layers, the FC model uses multiple hidden + layers, allowing it to learn hierarchical representations of the + input data. Deep learning models like this one can automatically + learn and extract complex features from the raw input, making them + exceptionally powerful for tasks such as land cover + classification.

+

To run an example of how to use the function + deepLearning find a detailed + notebook in tutorial No 11 + Deep + Learning Classification.

+ + + <bold>scikit-eo</bold> in the lecture room: +

scikit-eo can be part of a classroom as part of the + set of tools for environmental studies where a quantitative approach + and computer labs are required. Therefore, first of all an + appropriate introduction of Python, the basics of remote sensing, + and the relevance of environmental studies to address climate change + challenges or impacts of anthropogenic activity are needed. Lectures + can use the simplicity of scikit-eo routines to execute + supervised classification methods, + Principal Components Analysis, + Spectral Mixture Analysis, + Mapping forest or + land degradation and more types of analysis. + By reducing the number of required lines of code, students can focus + on the analysis and how the methods work rather than dealing with + complex and unnecessary programming tasks. Lecturers can structure + their computer labs using open data sources and integrate + scikit-eo to allow students to understand the + importance of the calibration and assessment metrics, get insights + about the classification mapping using satellite imagery, and + provide an introduction to more advanced methods that include + machine learning techniques.

+ + + <bold>scikit-eo</bold> as open source tool: +

As open-source software keeps transforming the landscape of + scientific research + (The + Turing Way Community et al., 2019), enabling collaboration, + reproducibility and transparency, scikit-eo was + explicitly developed as an open-source tool. scikit-eo + integrates most of the popular open source python libraries from the + so-called geo-python stack for remote sensing (e.g.,. + numpy, + pandas, + rasterio + and few more) to extent and create a centralised package for + advanced spatial analysis of remotely sensed data. The package + provides researchers and developers with a free, scalable, and + community-driven platform to process, analyse, and visualise + satellite imagery, specifically, centralising multiple functions’ + use for classification and mapping land cover.

+ + + + Functionalities + + Main tools +

Scikit-eo includes several algorithms to process + satellite images to assess complex environmental processes and + impacts. These include functions such as atmospheric correction, + machine learning and deep learning techniques, estimating area and + uncertainty, linear trend analysis, combination of optical and radar + images, and classification sub-pixel, and more. The main functions + are listed below:

+ + +

Main tools available for scikit-eo package. +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Name of functions/classesDescription
mlaSupervised Classification in Remote Sensing
calmlaCalibrating Supervised Classification in Remote + Sensing
confintervalMLInformation of Confusion Matrix by proportions of area, + overall accuracy, user’s accuracy with confidence interval + and estimated area with confidence interval as well.
deepLearningDeep Learning algorithms
atmosCorrRadiometric and Atmospheric Correction (currently + supporting Landsat)
rkmeansK-means classification
calkmeansThis function allows to calibrate the kmeans algorithm. + It is possible to obtain the best k value and the best + embedded algorithm in kmeans.
pcaPrincipal Components Analysis
linearTrendLinear trend is useful for mapping forest degradation or + land degradation
fusionrsThis algorithm allows to fuse images coming from + different spectral sensors (e.g., optical-optical, optical + and SAR or SAR-SAR). Among many of the qualities of this + function, it is possible to obtain the contribution (%) of + each variable in the fused image
smaSpectral Mixture Analysis - Sub-pixel + classification
tassCapThe Tasseled-Cap Transformation
+ +

For more information the reader is referred to the + scikit-eo + website.

+ + + + State of the field: +

Scikit-eo is built upon well-known packages and + libraries that support remote sensing analysis in python, but is + designed specifically to study land cover classification, and + providing tailored functionalities for environmental studies. It aims + to simplify the identification of patterns, changes, and trends for + environmental research. Like many other Python packages, + Scikit-eo makes use of Rasterio and + GDAL, which are essential for geospatial data + handling. Additionally, Scikit-eo is based on + Scikit-learn and tensorflow, a widely-used + machine learning libraries in Python that includes several algorithms + for classification, regression, clustering, and dimensionality + reduction. However, Scikit-eo includes machine learning + tools to remote sensing analysis. Another well-known library, + Geemap that provides interactive mapping capabilities + using Google Earth Engine and focuses more on visualization and data + exploration, while Scikit-eo is designed for deeper + analytical tasks using remote sensing data for land cover analysis. + The SITS package is particularly useful for time + series, while Scikit-eo provides functionalities for land + cover studies. torchgeo a popular Python library that + provides comprehensive deep learning functions for geospatial data. + However Scikit-eo integrates machine learning methods + that are particularly useful for analysing satellite imagery with + multiple bands for environmental studies. Lastly, + EO-learn can be considered the most aligned package + with Scikit-eo providing efficient processing and + analysis of satellite imagery capabilities but lacking the deep + learning and tailored functions specifically included for land cover + analysis.

+ + + Acknowledgments +

The authors would like to thank to David Montero Loaiza for the + idea of the package name and Qiusheng Wu for the suggestions that + helped to improve the package.

+ + + + + + + + + TarazonaYonatan + AlaitzZabala + XavierPons + AntoniBroquetas + JakubNowosad + Hamdi A.Zurqani + + Fusing Landsat and SAR data for mapping tropical deforestation through machine learning classification and the PVts-β non-seasonal detection approach + Canadian Journal of Remote Sensing + Taylor & Francis Online + 2021 + 47 + 10.1080/07038992.2021.1941823 + 677 + 696 + + + + + + TarazonaYonatan + Miyasiro-LópezMaría + + Monitoring tropical forest degradation using remote sensing. Challenges and opportunities in the Madre de Dios region, Peru + Remote Sensing Applications: Society and Environment + 2020 + 19 + 2352-9385 + https://www.sciencedirect.com/science/article/pii/S2352938519304124 + 10.1016/j.rsase.2020.100337 + 100337 + + + + + + + TarazonaYonatan + MantasVasco M. + PereiraA. J. S. C. + + Improving tropical deforestation detection through using photosynthetic vegetation time series – (PVts-β) + Ecological Indicators + 2018 + 94 + 1470-160X + https://www.sciencedirect.com/science/article/pii/S1470160X18305326 + 10.1016/j.ecolind.2018.07.012 + 367 + 379 + + + + + + OlofssonPontus + FoodyGiles M. + HeroldMartin + StehmanStephen V. + WoodcockCurtis E. + WulderMichael A. + + Good practices for estimating area and assessing accuracy of land change + Remote Sensing of Environment + 2014 + 148 + 0034-4257 + https://www.sciencedirect.com/science/article/pii/S0034425714000704 + 10.1016/j.rse.2014.02.015 + 42 + 57 + + + + + + PottLuan Pierre + AmadoTelmo Jorge Carneiro + SchwalbertRaí Augusto + CorassaGeomar Mateus + CiampittiIgnacio Antonio + + Satellite-based data fusion crop type classification and mapping in Rio Grande do Sul, Brazil + ISPRS Journal of Photogrammetry and Remote Sensing + 2021 + 176 + 0924-2716 + https://www.sciencedirect.com/science/article/pii/S0924271621001167 + 10.1016/j.isprsjprs.2021.04.015 + 196 + 210 + + + + + + ChavesMichel E. D. + PicoliMichelle C. A. + SanchesIeda D. + + Recent applications of Landsat 8/OLI and Sentinel-2/MSI for land use and land cover mapping: A systematic review + Remote Sensing + 2020 + 12 + 18 + 2072-4292 + https://www.mdpi.com/2072-4292/12/18/3062 + 10.3390/rs12183062 + + + + + + TrinderJohn + LiuQingxiang + + Assessing environmental impacts of urban growth using remote sensing + Geo-spatial Information Science + Taylor & Francis + 202001 + 23 + https://www.tandfonline.com/doi/abs/10.1080/10095020.2019.1710438 + 10.1080/10095020.2019.1710438 + 20 + 39 + + + + + + YangJun + GongPeng + FuRong + ZhangMinghua + ChenJingming + LiangShunlin + XuBing + ShiJiancheng + DickinsonRobert + + The role of satellite remote sensing in climate change studies + Nature Climate Change + Nature Publishing Group + 201309 + 3 + 1758-6798 + https://www.nature.com/articles/nclimate1908 + 10.1038/nclimate1908 + 875 + 883 + + + + + + Cavender-BaresJeannine + SchneiderFabian D. + SantosMaria João + ArmstrongAmanda + CarnavalAna + DahlinKyla M. + FatoyinboLola + HurttGeorge C. + SchimelDavid + TownsendPhilip A. + UstinSusan L. + WangZhihui + WilsonAdam M. + + Integrating remote sensing with ecology and evolution to advance biodiversity conservation + Nature Ecology & Evolution 2022 6:5 + Nature Publishing Group + 202203 + 6 + 2397-334X + https://www.nature.com/articles/s41559-022-01702-5 + 10.1038/s41559-022-01702-5 + 35332280 + 506 + 519 + + + + + + KucharczykMaja + HugenholtzChris H. + + Remote sensing of natural hazard-related disasters with small drones: Global trends, biases, and research opportunities + Remote Sensing of Environment + Elsevier + 202110 + 264 + 0034-4257 + 10.1016/J.RSE.2021.112577 + 112577 + + + + + + + The Turing Way Community + ArnoldBecky + BowlerLouise + GibsonSarah + HerterichPatricia + HigmanRosie + KrystalliAnna + MorleyAlexander + O’ReillyMartin + WhitakerKirstie + + The Turing Way: A handbook for reproducible data science + 201903 + https://zenodo.org/record/3233986 + 10.5281/ZENODO.3233986 + + + + + + HussMatthias + HockRegine + + Global-scale hydrological response to future glacier mass loss + Nature Climate Change + 2018 + 8 + 10.1038/s41558-017-0049-x + 135 + 140 + + + + + + HugonnetRomain + McNabbRobert + BerthierEtienne + MenounosBrian + NuthChristopher + GirodLuc + FarinottiDaniel + HussMatthias + DussaillantInes + BrunFanny + KääbAndreas + + Accelerated global glacier mass loss in the early twenty-first century + Nature + 2018 + 592 + 10.1038/s41586-021-03436-z + 726 + 731 + + + + +
diff --git a/joss.06692/paper.jats/workflow_updated.png b/joss.06692/paper.jats/workflow_updated.png new file mode 100644 index 0000000000..17f6cf1490 Binary files /dev/null and b/joss.06692/paper.jats/workflow_updated.png differ