{"title":"西非贝宁nokou<s:1>湖水葫芦的长期监测","authors":"Priscilla Baltezar , Ufuoma Ovienmhada , David Lagomasino , Lola Fatoyinbo , Seamus Lombardo , Metogbe Belfrid Djihouessi , Djigbo Félicien Badou , Gildas Tomavo , Fohla Mouftaou , Danielle Wood","doi":"10.1016/j.rsase.2025.101699","DOIUrl":null,"url":null,"abstract":"<div><div>Water hyacinth is a globally recognized invasive aquatic plant known for its significant environmental impact and the substantial costs associated with its management. Its proliferation has caused widespread damage across Lake Nokoué in southern Benin, home to fishing communities that practice traditional fishing techniques called <em>Acadja</em>. Although these fishing structures increase fishing yields, they also exacerbate the water hyacinth infestation rate. This study, therefore, models the extent of water hyacinth, <em>Acadja</em> with attached water hyacinth, other land, and other vegetation in the Lake Nokoué area using Landsat Collection 2 Tier 1 and Sentinel-1 C-band Synthetic Aperture Radar imagery from 2015 to 2022 with Random Forest machine learning. Seventeen predictors were selected to model each land cover, including five spectral indices, seven spectral bands, two radar bands, and three terrain predictors. The model mapped a total of 17,413.4 ha for water, 2907.5 ha for water hyacinth, 1780.6 ha for <em>Acadja</em>, 2128.6 ha for other land, and 8289 ha for other vegetation areas by the end of 2022. The rate of change in the region since 2015 was −6.8 % (water), +149.7 % (water hyacinth), +726.1 % (<em>Acadja</em>), −20.6 % (other land), and −15 % (other vegetation) for each class. A separate method was also tested to compare the supervised modeling to an unsupervised method. Otsu segmentation was used for the same study period. Otsu detected 614 ha of vegetation for 2015 and increased to 1133 ha by 2022, but results indicate this method is unreliable. Vegetation found in Lake Nokoué was also assessed monthly from 2000 to 2022 using manual segmentation of a harmonic Landsat time series. By 2022, results indicated that infestations consistently maxed out during December and January and exponentially expanded. Although infestations traditionally peaked during November and December, the study found that lake vegetation increased by 941 % and 304 % for the high- (September to December) and low-water (January to May) seasons.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"39 ","pages":"Article 101699"},"PeriodicalIF":4.5000,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Long-term monitoring of Water Hyacinth in Lake Nokoué, Benin, West Africa\",\"authors\":\"Priscilla Baltezar , Ufuoma Ovienmhada , David Lagomasino , Lola Fatoyinbo , Seamus Lombardo , Metogbe Belfrid Djihouessi , Djigbo Félicien Badou , Gildas Tomavo , Fohla Mouftaou , Danielle Wood\",\"doi\":\"10.1016/j.rsase.2025.101699\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Water hyacinth is a globally recognized invasive aquatic plant known for its significant environmental impact and the substantial costs associated with its management. Its proliferation has caused widespread damage across Lake Nokoué in southern Benin, home to fishing communities that practice traditional fishing techniques called <em>Acadja</em>. Although these fishing structures increase fishing yields, they also exacerbate the water hyacinth infestation rate. This study, therefore, models the extent of water hyacinth, <em>Acadja</em> with attached water hyacinth, other land, and other vegetation in the Lake Nokoué area using Landsat Collection 2 Tier 1 and Sentinel-1 C-band Synthetic Aperture Radar imagery from 2015 to 2022 with Random Forest machine learning. Seventeen predictors were selected to model each land cover, including five spectral indices, seven spectral bands, two radar bands, and three terrain predictors. The model mapped a total of 17,413.4 ha for water, 2907.5 ha for water hyacinth, 1780.6 ha for <em>Acadja</em>, 2128.6 ha for other land, and 8289 ha for other vegetation areas by the end of 2022. The rate of change in the region since 2015 was −6.8 % (water), +149.7 % (water hyacinth), +726.1 % (<em>Acadja</em>), −20.6 % (other land), and −15 % (other vegetation) for each class. A separate method was also tested to compare the supervised modeling to an unsupervised method. Otsu segmentation was used for the same study period. Otsu detected 614 ha of vegetation for 2015 and increased to 1133 ha by 2022, but results indicate this method is unreliable. Vegetation found in Lake Nokoué was also assessed monthly from 2000 to 2022 using manual segmentation of a harmonic Landsat time series. By 2022, results indicated that infestations consistently maxed out during December and January and exponentially expanded. Although infestations traditionally peaked during November and December, the study found that lake vegetation increased by 941 % and 304 % for the high- (September to December) and low-water (January to May) seasons.</div></div>\",\"PeriodicalId\":53227,\"journal\":{\"name\":\"Remote Sensing Applications-Society and Environment\",\"volume\":\"39 \",\"pages\":\"Article 101699\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Remote Sensing Applications-Society and Environment\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352938525002526\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Remote Sensing Applications-Society and Environment","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352938525002526","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Long-term monitoring of Water Hyacinth in Lake Nokoué, Benin, West Africa
Water hyacinth is a globally recognized invasive aquatic plant known for its significant environmental impact and the substantial costs associated with its management. Its proliferation has caused widespread damage across Lake Nokoué in southern Benin, home to fishing communities that practice traditional fishing techniques called Acadja. Although these fishing structures increase fishing yields, they also exacerbate the water hyacinth infestation rate. This study, therefore, models the extent of water hyacinth, Acadja with attached water hyacinth, other land, and other vegetation in the Lake Nokoué area using Landsat Collection 2 Tier 1 and Sentinel-1 C-band Synthetic Aperture Radar imagery from 2015 to 2022 with Random Forest machine learning. Seventeen predictors were selected to model each land cover, including five spectral indices, seven spectral bands, two radar bands, and three terrain predictors. The model mapped a total of 17,413.4 ha for water, 2907.5 ha for water hyacinth, 1780.6 ha for Acadja, 2128.6 ha for other land, and 8289 ha for other vegetation areas by the end of 2022. The rate of change in the region since 2015 was −6.8 % (water), +149.7 % (water hyacinth), +726.1 % (Acadja), −20.6 % (other land), and −15 % (other vegetation) for each class. A separate method was also tested to compare the supervised modeling to an unsupervised method. Otsu segmentation was used for the same study period. Otsu detected 614 ha of vegetation for 2015 and increased to 1133 ha by 2022, but results indicate this method is unreliable. Vegetation found in Lake Nokoué was also assessed monthly from 2000 to 2022 using manual segmentation of a harmonic Landsat time series. By 2022, results indicated that infestations consistently maxed out during December and January and exponentially expanded. Although infestations traditionally peaked during November and December, the study found that lake vegetation increased by 941 % and 304 % for the high- (September to December) and low-water (January to May) seasons.
期刊介绍:
The journal ''Remote Sensing Applications: Society and Environment'' (RSASE) focuses on remote sensing studies that address specific topics with an emphasis on environmental and societal issues - regional / local studies with global significance. Subjects are encouraged to have an interdisciplinary approach and include, but are not limited by: " -Global and climate change studies addressing the impact of increasing concentrations of greenhouse gases, CO2 emission, carbon balance and carbon mitigation, energy system on social and environmental systems -Ecological and environmental issues including biodiversity, ecosystem dynamics, land degradation, atmospheric and water pollution, urban footprint, ecosystem management and natural hazards (e.g. earthquakes, typhoons, floods, landslides) -Natural resource studies including land-use in general, biomass estimation, forests, agricultural land, plantation, soils, coral reefs, wetland and water resources -Agriculture, food production systems and food security outcomes -Socio-economic issues including urban systems, urban growth, public health, epidemics, land-use transition and land use conflicts -Oceanography and coastal zone studies, including sea level rise projections, coastlines changes and the ocean-land interface -Regional challenges for remote sensing application techniques, monitoring and analysis, such as cloud screening and atmospheric correction for tropical regions -Interdisciplinary studies combining remote sensing, household survey data, field measurements and models to address environmental, societal and sustainability issues -Quantitative and qualitative analysis that documents the impact of using remote sensing studies in social, political, environmental or economic systems