Centre dedocumentation
scientifique

Application of feature selection methods and machine learning algorithms for saltmarsh biomass estimation using Worldview-2 imagery / Sikdar M. M. Rasel in Geocarto international, vol 36 n° 10 ([01/06/2021])  

Public [article]  inGeocarto international > vol 36 n° 10 [01/06/2021] . - pp 1075-1099 Titre : Application of feature selection methods and machine learning algorithms for saltmarsh biomass estimation using Worldview-2 imagery Type de document : Article/Communication Auteurs : Sikdar M. M. Rasel, Auteur ; Hsing-Chung Chang, Auteur ; Timothy J. Ralph, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1075-1099 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] bande spectrale [Termes IGN] biomasse [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image multibande [Termes IGN] image Worldview [Termes IGN] marais salé [Termes IGN] modèle de simulation [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] régression [Termes IGN] variable Résumé : (Auteur) Assessing large scale plant productivity of coastal marshes is essential to understand the resilience of these systems to climate change. Two machine learning approaches, random forest (RF) and support vector machine (SVM) regression were tested to estimate biomass of a common saltmarshes species, salt couch grass (Sporobolus virginicus). Reflectance and vegetation indices derived from 8 bands of Worldview-2 multispectral data were used for four experiments to develop the biomass model. These four experiments were, Experiment-1: 8 bands of Worldview-2 image, Experiment-2: Possible combination of all bands of Worldview-2 for Normalized Difference Vegetation Index (NDVI) type vegetation indices, Experiment-3: Combination of bands and vegetation indices, Experiment-4: Selected variables derived from experiment-3 using variable selection methods. The main objectives of this study are (i) to recommend an affordable low cost data source to predict biomass of a common saltmarshes species, (ii) to suggest a variable selection method suitable for multispectral data, (iii) to assess the performance of RF and SVM for the biomass prediction model. Cross-validation of parameter optimizations for SVM showed that optimized parameter of ɛ-SVR failed to provide a reliable prediction. Hence, ν-SVR was used for the SVM model. Among the different variable selection methods, recursive feature elimination (RFE) selected a minimum number of variables (only 4) with an RMSE of 0.211 (kg/m2). Experiment-4 (only selected bands) provided the best results for both of the machine learning regression methods, RF (R2= 0.72, RMSE= 0.166 kg/m2) and SVR (R2= 0.66, RMSE = 0.200 kg/m2) to predict biomass. When a 10-fold cross validation of the RF model was compared with a 10-fold cross validation of SVR, a significant difference (p = Numéro de notice : A2021-367 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1624988 date de publication en ligne : 11/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1624988 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97729 [article]

A combined drought monitoring index based on multi-sensor remote sensing data and machine learning / Hongzhu Han in Geocarto international, vol 36 n° 10 ([01/06/2021])  

Public [article]  inGeocarto international > vol 36 n° 10 [01/06/2021] . - pp 1161-1177 Titre : A combined drought monitoring index based on multi-sensor remote sensing data and machine learning Type de document : Article/Communication Auteurs : Hongzhu Han, Auteur ; Jianjun Bai, Auteur ; Jianwu Yan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1161-1177 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] Chensi (Chine) [Termes IGN] classification par forêts aléatoires [Termes IGN] évapotranspiration [Termes IGN] humidité du sol [Termes IGN] image Terra-MODIS [Termes IGN] image TRMM-MI [Termes IGN] indice d'humidité [Termes IGN] indice de végétation [Termes IGN] précipitation [Termes IGN] sécheresse [Termes IGN] surveillance météorologique [Termes IGN] température au sol Résumé : (Auteur) The occurrence of drought is related to complicated interactions between many factors, such as precipitation, temperature, evapotranspiration and vegetation. In this study, the relationships between drought and precipitation, temperature, vegetation and evapotranspiration were investigated with a random forest (RF), and a new combined drought monitoring index (CDMI) was constructed. The effectiveness of the CDMI in monitoring drought in Shaanxi Province was verified by the in situ 1 ∼ 12-month standardized precipitation index (SPI); relative soil moisture (RSM) and four other commonly used remote sensing drought monitoring indices. The results show that CDMI is more correlated with the SPI and RSM than the four indices. Moreover, the spatial distributions of drought for the CDMI and RSM are similar. Therefore, the CDMI can be used to monitor droughts in Shaanxi Province, and machine learning can explore the relationships between various factors and establish a drought index without knowledge of the causal mechanisms of these factors. Numéro de notice : A2021-369 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1633423 date de publication en ligne : 27/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1633423 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97734 [article]

Evaluating the performance of hyperspectral leaf reflectance to detect water stress and estimation of photosynthetic capacities / Jingjing Zhou in Remote sensing, vol 13 n° 11 (June-1 2021)  

Public [article]  inRemote sensing > vol 13 n° 11 (June-1 2021) . - n° 2160 Titre : Evaluating the performance of hyperspectral leaf reflectance to detect water stress and estimation of photosynthetic capacities Type de document : Article/Communication Auteurs : Jingjing Zhou, Auteur ; Ya-Hao Zhang, Auteur ; Ze-Min Han, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 2160 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] Chine [Termes IGN] Citrus (genre) [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] feuille (végétation) [Termes IGN] image hyperspectrale [Termes IGN] photosynthèse [Termes IGN] réflectance végétale [Termes IGN] rendement agricole [Termes IGN] stress hydrique [Termes IGN] surveillance de la végétation Résumé : (auteur) Advanced techniques capable of early, rapid, and nondestructive detection of the impacts of drought on fruit tree and the measurement of the underlying photosynthetic traits on a large scale are necessary to meet the challenges of precision farming and full prediction of yield increases. We tested the application of hyperspectral reflectance as a high-throughput phenotyping approach for early identification of water stress and rapid assessment of leaf photosynthetic traits in citrus trees by conducting a greenhouse experiment. To this end, photosynthetic CO2 assimilation rate (Pn), stomatal conductance (Cond) and transpiration rate (Trmmol) were measured with gas-exchange approaches alongside measurements of leaf hyperspectral reflectance from citrus grown across a gradient of soil drought levels six times, during 20 days of stress induction and 13 days of rewatering. Water stress caused Pn, Cond, and Trmmol rapid and continuous decline throughout the entire drought period. The upper layer was more sensitive to drought than middle and lower layers. Water stress could also bring continuous and dynamic changes of the mean spectral reflectance and absorptance over time. After trees were rewatered, these differences were not obvious. The original reflectance spectra of the four water stresses were surprisingly of low diversity and could not track drought responses, whereas specific hyperspectral spectral vegetation indices (SVIs) and absorption features or wavelength position variables presented great potential. The following machine-learning algorithms: random forest (RF), support vector machine (SVM), gradient boost (GDboost), and adaptive boosting (Adaboost) were used to develop a measure of photosynthesis from leaf reflectance spectra. The performance of four machine-learning algorithms were assessed, and RF algorithm yielded the highest predictive power for predicting photosynthetic parameters (R2 was 0.92, 0.89, and 0.88 for Pn, Cond, and Trmmol, respectively). Our results indicated that leaf hyperspectral reflectance is a reliable and stable method for monitoring water stress and yield increase, with great potential to be applied in large-scale orchards. Numéro de notice : A2021-440 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13112160 date de publication en ligne : 31/05/2021 En ligne : https://doi.org/10.3390/rs13112160 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97826 [article]

Fractional vegetation cover estimation algorithm for FY-3B reflectance data based on random forest regression method / Duanyang Liu in Remote sensing, vol 13 n° 11 (June-1 2021)  

Public [article]  inRemote sensing > vol 13 n° 11 (June-1 2021) . - n° 2165 Titre : Fractional vegetation cover estimation algorithm for FY-3B reflectance data based on random forest regression method Type de document : Article/Communication Auteurs : Duanyang Liu, Auteur ; Kun Jia, Auteur ; Haiying jiang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 2165 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Chine [Termes IGN] classification par forêts aléatoires [Termes IGN] couvert végétal [Termes IGN] image Feng-Yun [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] réflectance végétale [Termes IGN] régression Résumé : (auteur) As an important land surface vegetation parameter, fractional vegetation cover (FVC) has been widely used in many Earth system ecological and climate models. In particular, high-quality and reliable FVC products on the global scale are important for the Earth surface process simulation and global change studies. Recently, the FengYun-3 (FY-3) series satellites, which are the second generation of Chinese meteorological satellites, launched with the polar orbit and provide continuous land surface observations on a global scale. However, there is rare studying on the FVC estimation using FY-3 reflectance data. Therefore, the FY-3B reflectance data were selected as the representative data to develop a FVC estimation algorithm in this study, which would investigate the capability of the FY-3 reflectance data on the global FVC estimation. The spatial–temporal validation over the regional area indicated that the FVC estimations generated by the proposed algorithm had reliable continuities. Furthermore, a satisfactory accuracy performance (R2 = 0.7336, RMSE = 0.1288) was achieved for the proposed algorithm based on the Earth Observation LABoratory (EOLAB) reference FVC data, which provided further evidence on the reliability and robustness of the proposed algorithm. All these results indicated that the FY-3 reflectance data were capable of generating a FVC estimation with reliable spatial–temporal continuities and accuracy. Numéro de notice : A2021-439 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13112165 date de publication en ligne : 31/05/2021 En ligne : https://doi.org/10.3390/rs13112165 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97824 [article]

Rapid ecosystem change at the southern limit of the Canadian Arctic, Torngat Mountains National Park / Emma L. Davis in Remote sensing, vol 13 n° 11 (June-1 2021)  

Public [article]  inRemote sensing > vol 13 n° 11 (June-1 2021) . - n° 2085 Titre : Rapid ecosystem change at the southern limit of the Canadian Arctic, Torngat Mountains National Park Type de document : Article/Communication Auteurs : Emma L. Davis, Auteur ; Andrew Trant, Auteur ; Robert G. Way, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 2085 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] arbuste [Termes IGN] Arctique [Termes IGN] Canada [Termes IGN] changement climatique [Termes IGN] classification par forêts aléatoires [Termes IGN] détection de changement [Termes IGN] écosystème [Termes IGN] écotone [Termes IGN] géostatistique [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] image Terra-MODIS [Termes IGN] modèle de simulation [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] parc naturel national [Termes IGN] régression logistique [Termes IGN] surveillance de la végétation [Termes IGN] toundra Résumé : (auteur) Northern protected areas guard against habitat and species loss but are themselves highly vulnerable to environmental change due to their fixed spatial boundaries. In the low Arctic, Torngat Mountains National Park (TMNP) of Canada, widespread greening has recently occurred alongside warming temperatures and regional declines in caribou. Little is known, however, about how biophysical controls mediate plant responses to climate warming, and available observational data are limited in temporal and spatial scope. In this study, we investigated the drivers of land cover change for the 9700 km2 extent of the park using satellite remote sensing and geostatistical modelling. Random forest classification was used to hindcast and simulate land cover change for four different land cover types from 1985 to 2019 with topographic and surface reflectance imagery (Landsat archive). The resulting land cover maps, in addition to topographic and biotic variables, were then used to predict where future shrub expansion is likely to occur using a binomial regression framework. Land cover hindcasts showed a 235% increase in shrub and a 105% increase in wet vegetation cover from 1985/89 to 2015/19. Shrub cover was highly persistent and displaced wet vegetation in southern, low-elevation areas, whereas wet vegetation expanded to formerly dry, mid-elevations. The predictive model identified both biotic (initial cover class, number of surrounding shrub neighbors), and topographic variables (elevation, latitude, and distance to the coast) as strong predictors of future shrub expansion. A further 51% increase in shrub cover is expected by 2039/43 relative to 2014 reference data. Establishing long-term monitoring plots within TMNP in areas where rapid vegetation change is predicted to occur will help to validate remote sensing observations and will improve our understanding of the consequences of change for biotic and abiotic components of the tundra ecosystem, including important cultural keystone species. Numéro de notice : A2021-442 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13112085 date de publication en ligne : 26/05/2021 En ligne : https://doi.org/10.3390/rs13112085 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97832 [article]

Automatic detection and classification of low-level orographic precipitation processes from space-borne radars using machine learning / Malarvizhi Arulraj in Remote sensing of environment, vol 257 (May 2021)  

Permalink

Integrating a forward feature selection algorithm, random forest, and cellular automata to extrapolate urban growth in the Tehran-Karaj region of Iran / Hossein Shafizadeh-Moghadam in Computers, Environment and Urban Systems, vol 87 (May 2021)  

Permalink

Mapping and quantification of the dwarf eelgrass Zostera noltii using a random forest algorithm on a SPOT 7 satellite image / Salma Benmokhtar in ISPRS International journal of geo-information, vol 10 n° 5 (May 2021)  

Permalink

A novel class-specific object-based method for urban change detection using high-resolution remote sensing imagery / Ting Bai in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 4 (April 2021)  

Permalink

Study on offshore seabed sediment classification based on particle size parameters using XGBoost algorithm / Fengfan Wang in Computers & geosciences, vol 149 (April 2021)  

Permalink

The delineation of tea gardens from high resolution digital orthoimages using mean-shift and supervised machine learning methods / Akhtar Jamil in Geocarto international, vol 36 n° 7 ([01/04/2021])  

Permalink

Anti-cross validation technique for constructing and boosting random subspace neural network ensembles for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 6 ([30/03/2021])  

Permalink

Analysis of plot-level volume increment models developed from machine learning methods applied to an uneven-aged mixed forest / Seyedeh Kosar Hamidi in Annals of Forest Science [en ligne], vol 78 n° 1 (March 2021)  

Permalink

Assessing land use–land cover change and soil erosion potential using a combined approach through remote sensing, RUSLE and random forest algorithm / Siddhartho Shekhar Paul in Geocarto international, vol 36 n° 4 ([01/03/2021])  

Permalink

Improving the unsupervised mapping of riparian bugweed in commercial forest plantations using hyperspectral data and LiDAR / Kabir Peerbhay in Geocarto international, vol 36 n° 4 ([01/03/2021])  

Permalink