Natural Numerical Networks for Natura 2000 habitats classification by satellite images

Natural numerical networks are introduced as a new classification algorithm based on the numerical solution of nonlinear partial differential equations of forward-backward diffusion type on complete graphs. The proposed natural numerical network is applied to open important environmental and nature conservation task, the automated identification of protected habitats by using satellite images. In the natural numerical network, the forward diffusion causes the movement of points in a feature space toward each other. The opposite effect, keeping the points away from each other, is caused by backward diffusion. This yields the desired classification. The natural numerical network contains a few parameters that are optimized in the learning phase of the method. After learning parameters and optimizing the topology of the network graph, classification necessary for habitat identification is performed. A relevancy map for each habitat is introduced as a tool for validating the classification and finding new Natura 2000 habitat appearances.

[1]  Karol Mikula,et al.  An automated segmentation of NATURA 2000 habitats from Sentinel-2 optical data , 2021, Discrete & Continuous Dynamical Systems - S.

[2]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[3]  D. King,et al.  A Range of Earth Observation Techniques for Assessing Plant Diversity , 2020 .

[4]  S. Franklin.  Remote Sensing for Sustainable Forest Management , 2001 .

[5]  Mewa Singh,et al.  Mapping and assessment of vegetation types in the tropical rainforests of the Western Ghats using multispectral Sentinel-2 and SAR Sentinel-1 satellite imagery , 2018, Remote Sensing of Environment.

[6]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[7]  K. Mikula,et al.  Semi-automatic segmentation of NATURA 2000 habitats in Sentinel-2 satellite images by evolving open curves , 2021, Discrete & Continuous Dynamical Systems - S.

[8]  Caspar A. Mücher,et al.  Integrating remote sensing in Natura 2000 habitat monitoring: prospects on the way forward , 2011 .

[9]  Bogdan Zagajewski,et al.  Assessment of Sentinel-2 Satellite Images and Random Forest Classifier for Rainforest Mapping in Gabon , 2020, Forests.

[10]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Markus Neteler,et al.  Open data and open source for remote sensing training in ecology , 2017, Ecological Informatics.

[12]  Erle C. Ellis,et al.  Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models , 2020 .

[13]  J. Friedman,et al.  Wave equations for graphs and the edge-based Laplacian , 2004 .

[14]  Eldad Haber,et al.  Stable architectures for deep neural networks , 2017, ArXiv.

[15]  Jon Atli Benediktsson,et al.  Big Data for Remote Sensing: Challenges and Opportunities , 2016, Proceedings of the IEEE.

[16]  R. Halvorsen,et al.  Consistency in land‐cover mapping: Influence of field workers, spatial scale and classification system , 2018 .

[17]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[18]  Eldad Haber,et al.  Reversible Architectures for Arbitrarily Deep Residual Neural Networks , 2017, AAAI.

[19]  Aditya Singh,et al.  Mapping Species Composition of Forests and Tree Plantations in Northeastern Costa Rica with an Integration of Hyperspectral and Multitemporal Landsat Imagery , 2015, Remote. Sens..

[20]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[21]  Frank Harary,et al.  Graph Theory , 2016 .

[22]  M. Bock,et al.  Object-oriented methods for habitat mapping at multiple scales – Case studies from Northern Germany and Wye Downs, UK , 2005 .

[23]  E. Smith.  Methods of Multivariate Analysis , 1997 .

[24]  Joel Friedman,et al.  Calculus on Graphs , 2004, ArXiv.

[25]  Michael Förster,et al.  Remote sensing for mapping natural habitats and their conservation status - New opportunities and challenges , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Juanle Wang,et al.  Forest Type Classification Based on Integrated Spectral-Spatial-Temporal Features and Random Forest Algorithm—A Case Study in the Qinling Mountains , 2019, Forests.

[27]  Karol Mikula,et al.  Semi-implicit finite volume scheme for solving nonlinear diffusion equations in image processing , 2001, Numerische Mathematik.

[28]  Stuart E. Dreyfus,et al.  Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure , 1990 .

[29]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Martin Kappas,et al.  Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery , 2017, Sensors.

[31]  R. Valentini,et al.  Discrimination of tropical forest types, dominant species, and mapping of functional guilds by hyperspectral and simulated multispectral Sentinel-2 data , 2016 .

[32]  Peng Liu,et al.  A survey of remote-sensing big data , 2015, Front. Environ. Sci..