Category: research

After several years of work, we are proud with my advisors to publish our paper about the tree species mapping using nine one-year Satellite Image Time Series from the Formosat-2 sensor. 🥂

📖 Read the article directly on Remote Sensing journal.

📎 Our main contributions can be synthesized as follows

• Spatial autocorrelation in the dataset highly overestimate the quality and so the extrapolation capabilites of the algorithm
• 📅 Optimal dates to map tree species are highly instable from one year to another
• Monospecific broadleaf plantations (Aspen, Red Oak and Eucalyptus) have high quality prediction, whereas conifer are difficult to map.
• ⛅ The use of the full Satellite Image Time Series can seriously decrease the quality due to clouds, cloud shadows

🗺️ Explore the map of tree species from the south of Toulouse

♻️ Reproducible research

In order to reproduce this study or to have tree species ground references suitable for remote sensing, we decided to share our reference samples publicly on Zenodo, the Open Science platform at the CERN Data.

Moreover, my own python library Museo ToolBox, allows to reproduce the whole paper and much more. For now, the code used for the paper is kept private, but it will be published at the end of my thesis.

I identified about 24 works, including 8 in peer-reviewed journals, that use the dzetsaka classification plugin. When I made this plugin, it was only to reproduce my work at the Guiana Amazonian Park. I didn’t expect it would be so much used and have so many downloads (about 55k today !).

I think must thank the Brazilian community because I found the majority of the people using dzetsaka is from there (Olá !). I don’t know why there are so much users in the Brazil then in the rest of the world, maybe because some researchers or teachers teach this plugin to their students. I notice that there also have been some great tutorials about dzetsaka published in youtube (Andre Q. Almeida UFS in 2017, Geoaplicada in 2018 and Anderson Medeiros of ClickGeo in 2019).

Algorithms used and dzetsaka evolution

The number of works per year is surprising. As we can see, 2019 is a great year with 15 works published online. The other years (2016,2017 and 2018) had about 3 to 4 works per year, so that’s quite a huge increase !

What algorithm is used in dzetsaka ? The wide majority performs the classification with the Gaussian Mixture Model implemented by the great Mathieu Fauvel. It is a efficient algorithm, with amazing speed capacities. However, Random-Forest often has better results, but takes longer to perform the fit and the predict process. GMM is provided by default in dzetsaka, you don’t need to install scikit-lit python library. I think that is the main reason for this gap.

Detailed of this work is available in Google docs.

Detailed list of the works (not limited), ordered by year

• Shaw, T. E., Gascoin, S., Mendoza, P. A., Pellicciotti, F., & McPhee, J. (2019). Snow depth patterns in a high mountain Andean catchment from satellite optical tri‐stereoscopic remote sensing. Water Resources Research.
• Rezende, P. S., & Rosa, R. Análise (2019). Temporal De Superfícies Impermeáveis Em Área Urbana Através Do Índice Built-up (BU).
• Leite, A. P. (2019). Discriminação do uso da terra na bacia hidrográfica do rio Araquá utilizando índices radiométricos.ISO 690
• de Oliveira, U. C., da Cunha Teixeira, L. F., Soares, F. F., Soares, P., & Mendonça, C. A. M. J. Avaliação (2019). Do Uso Do Solo E Cobertura Vegetal Na Zona De Amortecimento Do Parque Nacional De Ubajara, Em Ubajara, Cear.
• Ramdani, F. (2019). Recent expansion of oil palm plantation in the most eastern part of Indonesia: feature extraction with polarimetric SAR. International Journal of Remote Sensing, 40(19), 7371-7388.
• Fitz, P. R. (2019). Considerações sobre o uso de polígonos de amostragem em classificações supervisionadas de imagens de satélite. Caderno de Geografia, 29(59), 1124-1138.
• LEITE, A. C. C. (2019). Identificação e levantamento do estado de conservação de nascentes a partir de índices ambientais utilizando dados espaciais de alta resolução do projeto Pernambuco Tridimensional (PE3D) (Master’s thesis, Universidade Federal de Pernambuco).
• Escobar Soldevilla, M. Y. (2019). Mitigación de la erosión hídrica para la conservación del suelo en la subcuenca del río Ichu, Huancavelica.
• Toebat, E. (2019). Impact van Forest Stewardship Council (FSC) certificering op de levering van ecosysteemdiensten in boslandschappen van zuid-centraal Chili: een case study in het Nahuelbuta landschap.
• NEVES, Y. T. (2019). Modelagem hidrológica e hidrodinâmica acoplada 1D/2D utilizando imagens de perfilamento a laser (Master’s thesis, Universidade Federal de Pernambuco).
• Fitz, P. R., Vieira, J. C., & Soares, M. C. (2019). O uso de polígonos de amostragem em classificações supervisionadas de imagens de satélite. ENTRE-LUGAR, 10(19), 319-341.
• Baldantoni, P., Nolè, G., Lanorte, A., Tucci, B., Santarsiero, V., & Murgante, B. (2019, July). Trend Definition of Soil Consumption in the Period 1994–2014-Municipalities of Potenza, Matera and Melfi. In International Conference on Computational Science and Its Applications (pp. 683-691). Springer, Cham.
• Dewa, D. D., & Sejati, A. W. (2019). Pengaruh Perubahan Tutupan Lahan Terhadap Emisi GRK pada Wilayah Cepat Tumbuh di Kota Semarang. Jurnal Penginderaan Jauh Indonesia, 1(1), 24-31.
• Buzzi, M. A., Rueter, B. L., Ghermandi, L., & Maldonado, F. (2019). Influence of oil activity and sheep ranching on plant cover in the arid and semi-arid region of Patagonia, Argentina. Cuadernos de Investigación Geográfica, 45(2), 661-685.
• Sejati, A. W., Buchori, I., & Rudiarto, I. (2019). The spatio-temporal trends of urban growth and surface urban heat islands over two decades in the Semarang Metropolitan Region. Sustainable Cities and Society, 46, 101432.
• Tasca, F. A., Goerl, R. F., & Finotti, A. R. (2018). EFEITO DA RESOLUÇÃO ESPACIAL NA SIMULAÇÃO DE UMA TAXA DE DRENAGEM.
• Peixoto, C. S., & Taquari, R. Mudança (2018). no uso das terras na cabeceira do rio Miranda (MS): estudo de caso da sub-bacia do rio São Francisco (1986, 2000, 2018).
• González-Mesén, M. (2018). Comparación de dos metodologías de teledetección para la identificación de plantaciones forestales en la región Huetar Norte, Costa Rica.
• Potić, I. M., Ćurčić, N. B., Potić, M. M., Radovanović, M. M., & Potić, I., & Potić, M. (2017). Remote sensing machine learning algorithms in environmental stress detection: Case study of Pan-European south section of Corridor 10 in Serbia. The University Thought-Publication in Natural Sciences, 7(2), 41-46.
• Tretiakova, T. N. (2017). Remote Sensing Role in Environmental Stress Analysis: Еаst Serbia Wildfires Case Study (2007–2017). Journal of the Geographical Institute’Jovan Cvijic’SASA, 67(3).
• Furlan, A. R. (2017). Urbanização e riscos socioambientais em Erechim-RS.
• Rodrigues, L. T., UNITPAC, A., Silva, P. V., Medeiros, G. F., & Almeida, J. G. R. (2016). Mapeamento Aplicado a Estudo de Processos Erosivos às Margens da TO-010, Localizados no Trecho Entre Wanderlândia e Babaçulândia.
• Arruda, R. D. O. M., Dalmas, F. B., Militão, F. A., dos Santos, J. C., & Garcia, A. P. (2016). ANÁLISE GEOAMBIENTAL APLICADA AO ESTUDO DA RELAÇÃO ENTRE QUALIDADE DA ÁGUA E OCUPAÇÃO DAS MARGENS DA REPRESA GUARAPIRANGA (SÃO PAULO/SP), ENTRE 2004 E 2014. Revista Geociências-UNG-Ser, 15(1), 77-93.
• Santos, F. G. (2016). Monitoramento de áreas embargadas através de índice de vegetação na região sudoeste do Pará.
• Perbet, P., Karasiak, N., & Joubert, P. Cartographie des formations végétales particulières observables via télédétection.