Ecological Informatics最新文献_第3页

Fuzzy approaches provide improved spatial detection of coastal dune EU habitats

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-30 DOI: 10.1016/j.ecoinf.2025.103059

Emilia Pafumi , Claudia Angiolini , Giovanni Bacaro , Emanuele Fanfarillo , Tiberio Fiaschi , Duccio Rocchini , Simona Sarmati , Michele Torresani , Hannes Feilhauer , Simona Maccherini

Mapping habitats on coastal dunes, crucial yet highly vulnerable ecosystems, requires objectivity and repeatability, which are still lacking in the implementation of the Habitats Directive. Although remote sensing offers promising solutions, the effectiveness of distinguishing habitats on coastal dunes from satellite imagery remains uncertain. In this study, we compare crisp and fuzzy classification approaches using WorldView-3 imagery to map coastal dune habitats in two Natural Parks of Tuscany (Italy).

Field-collected vegetation data were classified into Annex I habitats of Habitats Directive and EUNIS habitats. Using field data as reference, we performed image classifications with a crisp method (Random Forests) and three fuzzy methods, namely Random Forests, Spectral Angle Mapper and Multiple Endmember Spectral Mixture Analysis. Metrics of overall accuracy and Mantel tests were used to compare the results.

EUNIS habitats exhibited the best performance in terms of classification accuracy, likely due to the simpler classification system. We observed a great disparity among habitats, with coastal dune scrubs and white dunes generally achieving the highest accuracy. Fuzzy classifications, despite yielding lower overall accuracy than the crisp classification, provided a more realistic representation of vegetation patterns, highlighting the inherent fuzziness of vegetation in coastal dunes. Despite challenges related to image resolution and habitat heterogeneity, combining satellite imagery with field surveys proved valuable for mapping coastal dune habitats, contributing essential data to the conservation of these fragile ecosystems. We provide a novel and effective tool, which will reduce the economic and physical efforts needed for habitat search and sampling in the field.

{"title":"Fuzzy approaches provide improved spatial detection of coastal dune EU habitats","authors":"Emilia Pafumi , Claudia Angiolini , Giovanni Bacaro , Emanuele Fanfarillo , Tiberio Fiaschi , Duccio Rocchini , Simona Sarmati , Michele Torresani , Hannes Feilhauer , Simona Maccherini","doi":"10.1016/j.ecoinf.2025.103059","DOIUrl":"10.1016/j.ecoinf.2025.103059","url":null,"abstract":"<div><div>Mapping habitats on coastal dunes, crucial yet highly vulnerable ecosystems, requires objectivity and repeatability, which are still lacking in the implementation of the Habitats Directive. Although remote sensing offers promising solutions, the effectiveness of distinguishing habitats on coastal dunes from satellite imagery remains uncertain. In this study, we compare crisp and fuzzy classification approaches using WorldView-3 imagery to map coastal dune habitats in two Natural Parks of Tuscany (Italy).</div><div>Field-collected vegetation data were classified into Annex I habitats of Habitats Directive and EUNIS habitats. Using field data as reference, we performed image classifications with a crisp method (Random Forests) and three fuzzy methods, namely Random Forests, Spectral Angle Mapper and Multiple Endmember Spectral Mixture Analysis. Metrics of overall accuracy and Mantel tests were used to compare the results.</div><div>EUNIS habitats exhibited the best performance in terms of classification accuracy, likely due to the simpler classification system. We observed a great disparity among habitats, with coastal dune scrubs and white dunes generally achieving the highest accuracy. Fuzzy classifications, despite yielding lower overall accuracy than the crisp classification, provided a more realistic representation of vegetation patterns, highlighting the inherent fuzziness of vegetation in coastal dunes. Despite challenges related to image resolution and habitat heterogeneity, combining satellite imagery with field surveys proved valuable for mapping coastal dune habitats, contributing essential data to the conservation of these fragile ecosystems. We provide a novel and effective tool, which will reduce the economic and physical efforts needed for habitat search and sampling in the field.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103059"},"PeriodicalIF":5.8,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prediction of some soil properties in volcanic soils using random forest modeling: A case study at chinyero special nature reserve (Tenerife, canary islands)

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-29 DOI: 10.1016/j.ecoinf.2025.103054

Víctor Manuel Romeo Jiménez , Jesús Santiago Notario del Pino , José Manuel Fernández-Guisuraga , Miguel Ángel Mejías Vera

Soil organic carbon (organic C) and pH are key soil properties and valuable indicators of soil quality, whereas phosphate retention capacity (P retention) is a diagnostic property to define andic soil properties and andic soils, with all of them typically interrelated in volcanic ash (i.e., andic) soils. In this paper, we examined the potential of a random forest (RF) regression model to predict field-measured soil pH, organic C and P retention capacity from several biophysical (type and fraction of the plant cover), bioclimatic (maximum temperature of the warmest month, precipitation and temperature seasonality, and precipitation of the driest quarter), and topographic (ruggedness and curvature of the slope) predictors in a protected forest area in Tenerife, Canary Islands. Piecewise structural equation modeling (pSEM) was subsequently used to unravel the complex, direct and indirect relationships between the biophysical, bioclimatic and topographic variables, and the selected soil properties. The RF regression model accounted for the properties of interest with varying degrees of accuracy, from organic C (R² = 0.67; RMSE = 29.86), to P retention capacity (R² = 0.44; RMSE = 18.84) and soil pH (R² = 0.31; RMSE = 0.43). The pSEM model revealed that P retention capacity is strongly linked to organic C in volcanic ash soils, and thus indirectly to the environmental variables shaping organic C variability, namely fractional vegetation cover and precipitation seasonality.

{"title":"Prediction of some soil properties in volcanic soils using random forest modeling: A case study at chinyero special nature reserve (Tenerife, canary islands)","authors":"Víctor Manuel Romeo Jiménez , Jesús Santiago Notario del Pino , José Manuel Fernández-Guisuraga , Miguel Ángel Mejías Vera","doi":"10.1016/j.ecoinf.2025.103054","DOIUrl":"10.1016/j.ecoinf.2025.103054","url":null,"abstract":"<div><div>Soil organic carbon (organic C) and pH are key soil properties and valuable indicators of soil quality, whereas phosphate retention capacity (P retention) is a diagnostic property to define andic soil properties and andic soils, with all of them typically interrelated in volcanic ash (i.e., andic) soils. In this paper, we examined the potential of a random forest (RF) regression model to predict field-measured soil pH, organic C and P retention capacity from several biophysical (type and fraction of the plant cover), bioclimatic (maximum temperature of the warmest month, precipitation and temperature seasonality, and precipitation of the driest quarter), and topographic (ruggedness and curvature of the slope) predictors in a protected forest area in Tenerife, Canary Islands. Piecewise structural equation modeling (pSEM) was subsequently used to unravel the complex, direct and indirect relationships between the biophysical, bioclimatic and topographic variables, and the selected soil properties. The RF regression model accounted for the properties of interest with varying degrees of accuracy, from organic C (R<sup>2</sup> = 0.67; RMSE = 29.86), to P retention capacity (R<sup>2</sup> = 0.44; RMSE = 18.84) and soil pH (R<sup>2</sup> = 0.31; RMSE = 0.43). The pSEM model revealed that P retention capacity is strongly linked to organic C in volcanic ash soils, and thus indirectly to the environmental variables shaping organic C variability, namely fractional vegetation cover and precipitation seasonality.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103054"},"PeriodicalIF":5.8,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Feature engineering on climate data with machine learning to understand time-lagging effects in pasture yield prediction

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-28 DOI: 10.1016/j.ecoinf.2025.103011

Thirunavukarasu Balasubramaniam , Wathsala Anupama Mohotti , Kenneth Sabir , Richi Nayak

Pastures are a primary food source for livestock in Australia, with various pasture species grown in rotations. Accurate prediction of pasture availability is critical for effective farm management, livestock growth, and maintaining the supply chain. Environmental factors, particularly climate, heavily influence pasture yield. However, different pasture species respond to climate attributes with varying time lags; for example, one species might be more influenced by last week’s weather while another by the previous month’s highlighting the nuanced temporal dependencies. This time-lagging effect complicates the development of machine-learning models that can learn the temporal dependencies to predict pasture yield. To address this, our study proposes an averaging-based feature engineering approach, effectively capturing the varying temporal dependencies across pasture species and also allowing interpretation of the dependencies. Utilizing remote sensing and climate data, covering 196 farms (and 6885 paddocks) across Australia, we applied several machine learning techniques, including XGBoost, random forest, linear regression, deep neural networks, stacking, and bootstrapping. Our results show that incorporating averaging-based feature-engineered climate attributes significantly improves pasture yield predictions, with enhancements of up to 20.28%, 31.81%, and 31.11% across the three evaluation measures, RMSE, MAE, and R

^{2}

, respectively. This approach also enhances interpretability, revealing diverse time-lagging effects on different pasture species. XGBoost-based feature importance analysis further unveils insights into the influence of each climate attribute and its temporal dependencies on pasture yield.

{"title":"Feature engineering on climate data with machine learning to understand time-lagging effects in pasture yield prediction","authors":"Thirunavukarasu Balasubramaniam , Wathsala Anupama Mohotti , Kenneth Sabir , Richi Nayak","doi":"10.1016/j.ecoinf.2025.103011","DOIUrl":"10.1016/j.ecoinf.2025.103011","url":null,"abstract":"<div><div>Pastures are a primary food source for livestock in Australia, with various pasture species grown in rotations. Accurate prediction of pasture availability is critical for effective farm management, livestock growth, and maintaining the supply chain. Environmental factors, particularly climate, heavily influence pasture yield. However, different pasture species respond to climate attributes with varying time lags; for example, one species might be more influenced by last week’s weather while another by the previous month’s highlighting the nuanced temporal dependencies. This time-lagging effect complicates the development of machine-learning models that can learn the temporal dependencies to predict pasture yield. To address this, our study proposes an averaging-based feature engineering approach, effectively capturing the varying temporal dependencies across pasture species and also allowing interpretation of the dependencies. Utilizing remote sensing and climate data, covering 196 farms (and 6885 paddocks) across Australia, we applied several machine learning techniques, including XGBoost, random forest, linear regression, deep neural networks, stacking, and bootstrapping. Our results show that incorporating averaging-based feature-engineered climate attributes significantly improves pasture yield predictions, with enhancements of up to 20.28%, 31.81%, and 31.11% across the three evaluation measures, RMSE, MAE, and R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>, respectively. This approach also enhances interpretability, revealing diverse time-lagging effects on different pasture species. XGBoost-based feature importance analysis further unveils insights into the influence of each climate attribute and its temporal dependencies on pasture yield.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103011"},"PeriodicalIF":5.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Clean fishing: Construction of prediction model for high-catch Antarctic krill (Euphausia superba) fishing grounds based on deep learning and dynamic sliding window methods

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-27 DOI: 10.1016/j.ecoinf.2025.103047

Haibin Han , Bohui Jiang , Hongliang Huang , Yang Li , Jianghua Sui , Guoqing Zhao , Yuhan Wang , Heng Zhang , Shenglong Yang , Yongchuang Shi

Achieving energy-efficient, precise, and overall efficient production of Antarctic krill (Euphausia superba) is critical for realizing sustainable and ecological fisheries in the context of ongoing natural and anthropogenic climate change. In this study, we comprehensively analyzed commercial E. superba statistics and multivariate marine environmental data from 2010 to 2022 using the gravity center of the fishing ground method, dynamic sliding window, 3DCNN, and 3DCNN-ConvLSTM models. Results: 1) Inter-annual and inter-weekly catch varied significantly, with the total weekly catch evenly distributed between 0 and 2600 tons. The annual gravity center of the fishing grounds varied considerably between years and was mainly concentrated around the islands and in the strait. 2) Neither long- nor short-time-series historical data led to the best prediction. The optimal sliding window size for the 3DCNN was 4, whereas it was 11 for the 3DCNN-ConvLSTM model. 3) Climate change must be considered when selecting data, and the addition of biased data may negatively affect the model's predictive performance. 4) When using an optimal sliding window, the 3DCNN model outperformed the 3DCNN-ConvLSTM model. 5) The 3DCNN model tends to learn information about the environmental variables with the most significant differences in different categories of fishing grounds. This study aids in efficient selection of the most relevant historical data and an optimal model for developing a prediction model for high-catch fishing grounds, thereby providing a scientific foundation for clean production, sustainable development, and effective management of the E. superba fishery.

{"title":"Clean fishing: Construction of prediction model for high-catch Antarctic krill (Euphausia superba) fishing grounds based on deep learning and dynamic sliding window methods","authors":"Haibin Han , Bohui Jiang , Hongliang Huang , Yang Li , Jianghua Sui , Guoqing Zhao , Yuhan Wang , Heng Zhang , Shenglong Yang , Yongchuang Shi","doi":"10.1016/j.ecoinf.2025.103047","DOIUrl":"10.1016/j.ecoinf.2025.103047","url":null,"abstract":"<div><div>Achieving energy-efficient, precise, and overall efficient production of Antarctic krill (<em>Euphausia superba</em>) is critical for realizing sustainable and ecological fisheries in the context of ongoing natural and anthropogenic climate change. In this study, we comprehensively analyzed commercial <em>E. superba</em> statistics and multivariate marine environmental data from 2010 to 2022 using the gravity center of the fishing ground method, dynamic sliding window, 3DCNN, and 3DCNN-ConvLSTM models. Results: 1) Inter-annual and inter-weekly catch varied significantly, with the total weekly catch evenly distributed between 0 and 2600 tons. The annual gravity center of the fishing grounds varied considerably between years and was mainly concentrated around the islands and in the strait. 2) Neither long- nor short-time-series historical data led to the best prediction. The optimal sliding window size for the 3DCNN was 4, whereas it was 11 for the 3DCNN-ConvLSTM model. 3) Climate change must be considered when selecting data, and the addition of biased data may negatively affect the model's predictive performance. 4) When using an optimal sliding window, the 3DCNN model outperformed the 3DCNN-ConvLSTM model. 5) The 3DCNN model tends to learn information about the environmental variables with the most significant differences in different categories of fishing grounds. This study aids in efficient selection of the most relevant historical data and an optimal model for developing a prediction model for high-catch fishing grounds, thereby providing a scientific foundation for clean production, sustainable development, and effective management of the <em>E. superba</em> fishery.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103047"},"PeriodicalIF":5.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated curation of spatial metadata in environmental monitoring data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-27 DOI: 10.1016/j.ecoinf.2025.103038

İlhan Mutlu , Jörg Hackermüller , Jana Schor

Spatial data accuracy in environmental monitoring is crucial for practical large-scale data analytics and the development of AI models. In this context, spatial data is metadata and faces the same challenges as any other metadata, like missing values, false or contradicting information, formatting problems of textual data and numbers, the usage of different languages, and more. These issues severely limit the usability of the data.

With this study, we provide an automatic approach, CleanGeoStreamR, to resolve as many of these issues as possible for the spatially annotated environmental monitoring database. We substantially increased the quality of the spatial metadata and, therefore, the quantity of data points that can be used in large-scale data analytics and AI applications.

Further, our goal is to raise awareness about the issues related to spatial metadata and promote the implementation of our concepts in other environmental monitoring data sources. Advanced understanding and the availability of automatic approaches like the presented method will substantially contribute to making environmental monitoring data FAIR and enhance its usability in the era of Big Data and AI.

{"title":"Automated curation of spatial metadata in environmental monitoring data","authors":"İlhan Mutlu , Jörg Hackermüller , Jana Schor","doi":"10.1016/j.ecoinf.2025.103038","DOIUrl":"10.1016/j.ecoinf.2025.103038","url":null,"abstract":"<div><div>Spatial data accuracy in environmental monitoring is crucial for practical large-scale data analytics and the development of AI models. In this context, spatial data is metadata and faces the same challenges as any other metadata, like missing values, false or contradicting information, formatting problems of textual data and numbers, the usage of different languages, and more. These issues severely limit the usability of the data.</div><div>With this study, we provide an automatic approach, CleanGeoStreamR, to resolve as many of these issues as possible for the spatially annotated environmental monitoring database. We substantially increased the quality of the spatial metadata and, therefore, the quantity of data points that can be used in large-scale data analytics and AI applications.</div><div>Further, our goal is to raise awareness about the issues related to spatial metadata and promote the implementation of our concepts in other environmental monitoring data sources. Advanced understanding and the availability of automatic approaches like the presented method will substantially contribute to making environmental monitoring data FAIR and enhance its usability in the era of Big Data and AI.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103038"},"PeriodicalIF":5.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Phytoplankton growth and succession driven by topography and hydrodynamics in seasonal ice-covered lakes

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-27 DOI: 10.1016/j.ecoinf.2025.103053

Ziyue Zhao , Yanfeng Wu , Y. Jun Xu , Yexiang Yu , Guangxin Zhang , Dehua Mao , Xuemei Liu , Changlei Dai

Understanding how underwater topography affects phytoplankton succession by influencing hydrodynamics is crucial for maintaining the ecological health of lakes. However, there is a lack of in-depth research that accurately depicts underwater topography and coupleing hydrodynamics to establish the reproduction and migration mechanisms of phytoplankton, especially in seasonal ice-covered lakes. A typical seasonally ice-covered lake, Lake Chagan, was selected, and 164 water column and plankton samples were collected in 2023. An integrated underwater topographic-hydrodynamic model was constructed based on topographic data from 597 exploration points and long-term hydrological and meteorological observational data. The dominant algal species and their three-dimensional distribution and succession processes during different periods were studied in detail. The effects of topographic factors (relief, surface curvature, water depth, slope gradient, roughness, and slope aspect) on the hydrodynamic field and phytoplankton distribution were discussed. The results showed that the phytoplankton species diversity was higher in the bottom water column during the non-ice-covered period (March to October). The dominant species of phytoplankton varied with seasons, with diatoms dominating in the ice-covered period and harmful phytoplankton such as cyanobacteria in the non-ice-covered period. The biomass and biomass density of cyanobacteria were also higher than those of other phytoplankton. Phytoplankton species diversity and richness indices in the surface water column had a significant combined effect on the entire lake ecosystem. Surface curvature and slope gradient were the main factors affecting flow velocity during the non-ice-covered period (p ≤ 0.05, r = −0.58 and − 0.62), directly affecting the spatial distribution of cyanobacterial biomass (p ≤ 0.05, r = 0.65; p ≤ 0.01, r = −0.71). Therefore, attention should be paid to the surface curvature and slope of the sediment when controlling cyanobacterial blooms via by sediment dredging. These studies explored the behavior of phytoplankton in response to their fluid environment from a combined biological and physical-dynamic perspective and provided an effective reference for the water environment management of seasonal ice-covered lakes with harmful algal blooms.

{"title":"Phytoplankton growth and succession driven by topography and hydrodynamics in seasonal ice-covered lakes","authors":"Ziyue Zhao , Yanfeng Wu , Y. Jun Xu , Yexiang Yu , Guangxin Zhang , Dehua Mao , Xuemei Liu , Changlei Dai","doi":"10.1016/j.ecoinf.2025.103053","DOIUrl":"10.1016/j.ecoinf.2025.103053","url":null,"abstract":"<div><div>Understanding how underwater topography affects phytoplankton succession by influencing hydrodynamics is crucial for maintaining the ecological health of lakes. However, there is a lack of in-depth research that accurately depicts underwater topography and coupleing hydrodynamics to establish the reproduction and migration mechanisms of phytoplankton, especially in seasonal ice-covered lakes. A typical seasonally ice-covered lake, Lake Chagan, was selected, and 164 water column and plankton samples were collected in 2023. An integrated underwater topographic-hydrodynamic model was constructed based on topographic data from 597 exploration points and long-term hydrological and meteorological observational data. The dominant algal species and their three-dimensional distribution and succession processes during different periods were studied in detail. The effects of topographic factors (relief, surface curvature, water depth, slope gradient, roughness, and slope aspect) on the hydrodynamic field and phytoplankton distribution were discussed. The results showed that the phytoplankton species diversity was higher in the bottom water column during the non-ice-covered period (March to October). The dominant species of phytoplankton varied with seasons, with diatoms dominating in the ice-covered period and harmful phytoplankton such as cyanobacteria in the non-ice-covered period. The biomass and biomass density of cyanobacteria were also higher than those of other phytoplankton. Phytoplankton species diversity and richness indices in the surface water column had a significant combined effect on the entire lake ecosystem. Surface curvature and slope gradient were the main factors affecting flow velocity during the non-ice-covered period (<em>p</em> <em>≤</em> <em>0.05</em>, <em>r = −0.58</em> and <em>− 0.62</em>), directly affecting the spatial distribution of cyanobacterial biomass (<em>p</em> <em>≤</em> <em>0.05</em>, <em>r = 0.65</em>; <em>p</em> <em>≤</em> <em>0.01</em>, <em>r = −0.71</em>). Therefore, attention should be paid to the surface curvature and slope of the sediment when controlling cyanobacterial blooms via by sediment dredging. These studies explored the behavior of phytoplankton in response to their fluid environment from a combined biological and physical-dynamic perspective and provided an effective reference for the water environment management of seasonal ice-covered lakes with harmful algal blooms.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103053"},"PeriodicalIF":5.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mapping forest-agroforest frontiers in the Peruvian Amazon with deep learning and PlanetScope satellite data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-27 DOI: 10.1016/j.ecoinf.2025.103034

Wanting Yang, Daniel Ortiz-Gonzalo, Xiaoye Tong, Dimitri Gominski, Rasmus Fensholt

Monitoring complex and dynamic land systems such as tropical agroforests using remote sensing presents a significant challenge in ecological research. Traditional mapping methods are hindered not only by spectral similarity between agroforests and forests, but also by the spatial heterogeneity of forest-agroforest frontiers and the high data demand at large scales is an additional challenge. In this study, we aim to develop a modeling framework to distinguish between forests, secondary forests, agroforests (e.g. shade-grown perennials), and non-tree agricultural classes (e.g. active cropland, grassland, young fallow) in the Peruvian Amazon. To achieve this, we combine deep learning and remote sensing data, including 3-m PlanetScope satellite imagery, a Digital Elevation Model (DEM), and temporal data from the Landtrendr change detection algorithm. We conducted a sequence of modeling experiments involving different complexity of the data inputs and output classes, with overall accuracies ranging from 28.6 % to 82.9 %. Integrating a DEM as an additional helped the generalization of models across different geographical sites but did not improve the overall accuracy, whereas adding temporal information did not improve generalization or accuracy. Challenges arise in accurately identifying successional land cover types, particularly young fallow, which exhibits spectral similarity to other classes. Reducing the target classes from seven to four was found to considerably improve the accuracy of the predictions. Our findings contribute to distinguishing agroforests from forests at a large scale, providing insights into previously undetected tree-covered land uses and thus informing on sustainable ecosystem management. Yet, our results underscore the limitations of remote sensing in heterogeneous forest-agriculture landscapes and emphasize the need for further research to address persistent challenges and improve classification accuracy for monitoring global environmental change.

{"title":"Mapping forest-agroforest frontiers in the Peruvian Amazon with deep learning and PlanetScope satellite data","authors":"Wanting Yang, Daniel Ortiz-Gonzalo, Xiaoye Tong, Dimitri Gominski, Rasmus Fensholt","doi":"10.1016/j.ecoinf.2025.103034","DOIUrl":"10.1016/j.ecoinf.2025.103034","url":null,"abstract":"<div><div>Monitoring complex and dynamic land systems such as tropical agroforests using remote sensing presents a significant challenge in ecological research. Traditional mapping methods are hindered not only by spectral similarity between agroforests and forests, but also by the spatial heterogeneity of forest-agroforest frontiers and the high data demand at large scales is an additional challenge. In this study, we aim to develop a modeling framework to distinguish between forests, secondary forests, agroforests (e.g. shade-grown perennials), and non-tree agricultural classes (e.g. active cropland, grassland, young fallow) in the Peruvian Amazon. To achieve this, we combine deep learning and remote sensing data, including 3-m PlanetScope satellite imagery, a Digital Elevation Model (DEM), and temporal data from the Landtrendr change detection algorithm. We conducted a sequence of modeling experiments involving different complexity of the data inputs and output classes, with overall accuracies ranging from 28.6 % to 82.9 %. Integrating a DEM as an additional helped the generalization of models across different geographical sites but did not improve the overall accuracy, whereas adding temporal information did not improve generalization or accuracy. Challenges arise in accurately identifying successional land cover types, particularly young fallow, which exhibits spectral similarity to other classes. Reducing the target classes from seven to four was found to considerably improve the accuracy of the predictions. Our findings contribute to distinguishing agroforests from forests at a large scale, providing insights into previously undetected tree-covered land uses and thus informing on sustainable ecosystem management. Yet, our results underscore the limitations of remote sensing in heterogeneous forest-agriculture landscapes and emphasize the need for further research to address persistent challenges and improve classification accuracy for monitoring global environmental change.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103034"},"PeriodicalIF":5.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143227476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the feasibility of GF1-WFV data in estimating SPAD using spatiotemporal fusion algorithms

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-25 DOI: 10.1016/j.ecoinf.2025.103035

Annan Zeng , Jianli Ding , Jinjie Wang , Lijing Han , Haiyan Han , Shuang Zhao , Xiangyu Ge

Remote sensing technology provides an effective means for continuously assessing the chlorophyll content in plants on a broad scale. Given the challenges associated with satellite image quality and spatiotemporal resolution, spatiotemporal fusion algorithms for estimating vegetation chlorophyll content have garnered significant attention in recent years. In this study, we evaluated the performance of four fusion algorithms fusing Gaofen-1 WFV and MODIS data while also exploring their fusion accuracy. A random forest regression model was developed using the fused images and measured SPAD (Soil and Plant Analyzer Development) values, enabling large-scale, accurate, and dynamic monitoring of vegetation chlorophyll content. The results indicate that (1) all four fusion algorithms can effectively address the issue of missing images; (2) the constructed random forest regression model accurately estimates SPAD values; and (3) among the three vegetation indices that exhibit a strong correlation with SPAD values, the fusion strategy “Index-then-Blend” outperforms “Blend-then-Index.” This study provides comprehensive insights into dynamic and large-scale monitoring of vegetation chlorophyll content, particularly in scenarios in which satellite imagery is unavailable.

{"title":"Exploring the feasibility of GF1-WFV data in estimating SPAD using spatiotemporal fusion algorithms","authors":"Annan Zeng , Jianli Ding , Jinjie Wang , Lijing Han , Haiyan Han , Shuang Zhao , Xiangyu Ge","doi":"10.1016/j.ecoinf.2025.103035","DOIUrl":"10.1016/j.ecoinf.2025.103035","url":null,"abstract":"<div><div>Remote sensing technology provides an effective means for continuously assessing the chlorophyll content in plants on a broad scale. Given the challenges associated with satellite image quality and spatiotemporal resolution, spatiotemporal fusion algorithms for estimating vegetation chlorophyll content have garnered significant attention in recent years. In this study, we evaluated the performance of four fusion algorithms fusing Gaofen-1 WFV and MODIS data while also exploring their fusion accuracy. A random forest regression model was developed using the fused images and measured SPAD (Soil and Plant Analyzer Development) values, enabling large-scale, accurate, and dynamic monitoring of vegetation chlorophyll content. The results indicate that (1) all four fusion algorithms can effectively address the issue of missing images; (2) the constructed random forest regression model accurately estimates SPAD values; and (3) among the three vegetation indices that exhibit a strong correlation with SPAD values, the fusion strategy “Index-then-Blend” outperforms “Blend-then-Index.” This study provides comprehensive insights into dynamic and large-scale monitoring of vegetation chlorophyll content, particularly in scenarios in which satellite imagery is unavailable.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103035"},"PeriodicalIF":5.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An automatic identification method of common species based on ensemble learning

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-25 DOI: 10.1016/j.ecoinf.2025.103046

Hao-Xuan Li , Mei Zhang , De-Yao Meng , Bo Geng , Zu-Kui Li , Chuan-Feng Huang , Wen-Kang Li , Han-Lin Jiang , Rong-Hai Wu , Xiao-Wei Li , Ben-Hui Chen , Deng-Qi Yang , Guo-Peng Ren

Camera traps are an important tool for animal resource surveys, allowing non-invasive wildlife image capture and providing essential data for species identification. However, the vast number of images generated requires significant manual effort for sorting, limiting its development in biodiversity studies. Deep learning offers a promising solution by accurately identifying species from large datasets, enhancing processing efficiency, and reducing costs. While existing deep learning methods have achieved significant success in species identification, they often struggle with accurately recognizing all species due to the class imbalance prevalent in camera trap datasets, which limits the application of deep learning models in biodiversity monitoring. This study proposed an ensemble learning method based on common species modeling to automatically identify common species, which constitute the majority of camera trap datasets. We utilized three base models: ResNet-18, ResNeXt-50, and ViT-Base to validate our method on the Snapshot Serengeti dataset. The experimental results showed that the performance of the ensemble learning method improved with the performance of the selected base model. When ResNeXt-50 was used as the base model, the recall and precision of all common species on the in-sample test set exceeded 98 % and 97 %, respectively, except for Gazelle Grants. The automation rate of the ensemble model was 80.67 %, and the omission error of rare species was 2.03 %. On the out-of-sample test set, all species except for Zebra, Buffalo, and Gazelle Grants had a recall of over 95 %. Apart from Gazelle Grants, the precision for the other species was above 90 %. The automation rate of the ensemble model was 72.27 %, and the omission error of rare species was 5.31 %. Our method achieved the automatic identification of common species, thus reducing the workload of manual sorting. In addition, our approach separated rare species images from the dataset by identifying common species, minimizing potential omission errors. As a result, ecologists focusing on rare species only need to handle rare species images that only represent a small proportion of the dataset.

{"title":"An automatic identification method of common species based on ensemble learning","authors":"Hao-Xuan Li , Mei Zhang , De-Yao Meng , Bo Geng , Zu-Kui Li , Chuan-Feng Huang , Wen-Kang Li , Han-Lin Jiang , Rong-Hai Wu , Xiao-Wei Li , Ben-Hui Chen , Deng-Qi Yang , Guo-Peng Ren","doi":"10.1016/j.ecoinf.2025.103046","DOIUrl":"10.1016/j.ecoinf.2025.103046","url":null,"abstract":"<div><div>Camera traps are an important tool for animal resource surveys, allowing non-invasive wildlife image capture and providing essential data for species identification. However, the vast number of images generated requires significant manual effort for sorting, limiting its development in biodiversity studies. Deep learning offers a promising solution by accurately identifying species from large datasets, enhancing processing efficiency, and reducing costs. While existing deep learning methods have achieved significant success in species identification, they often struggle with accurately recognizing all species due to the class imbalance prevalent in camera trap datasets, which limits the application of deep learning models in biodiversity monitoring. This study proposed an ensemble learning method based on common species modeling to automatically identify common species, which constitute the majority of camera trap datasets. We utilized three base models: ResNet-18, ResNeXt-50, and ViT-Base to validate our method on the Snapshot Serengeti dataset. The experimental results showed that the performance of the ensemble learning method improved with the performance of the selected base model. When ResNeXt-50 was used as the base model, the recall and precision of all common species on the in-sample test set exceeded 98 % and 97 %, respectively, except for Gazelle Grants. The automation rate of the ensemble model was 80.67 %, and the omission error of rare species was 2.03 %. On the out-of-sample test set, all species except for Zebra, Buffalo, and Gazelle Grants had a recall of over 95 %. Apart from Gazelle Grants, the precision for the other species was above 90 %. The automation rate of the ensemble model was 72.27 %, and the omission error of rare species was 5.31 %. Our method achieved the automatic identification of common species, thus reducing the workload of manual sorting. In addition, our approach separated rare species images from the dataset by identifying common species, minimizing potential omission errors. As a result, ecologists focusing on rare species only need to handle rare species images that only represent a small proportion of the dataset.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103046"},"PeriodicalIF":5.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DeepFins: Capturing dynamics in underwater videos for fish detection

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-25 DOI: 10.1016/j.ecoinf.2025.103013

Ahsan Jalal , Ahmad Salman , Ajmal Mian , Salman Ghafoor , Faisal Shafait

The monitoring of fish in their natural habitat plays a crucial role in anticipating changes within marine ecosystems. Marine scientists have a preference for automated, unrestricted underwater video-based sampling due to its non-invasive nature and its ability to yield desired outcomes more rapidly compared to manual sampling. Generally, research on automated video-based detection using computer vision and machine learning has been confined to controlled environments. Additionally, these solutions encounter difficulties when applied in real-world settings characterized by substantial environmental variability, including issues like poor visibility in unregulated underwater videos, challenges in capturing fish-related visual characteristics, and background interference. In response, we propose a hybrid solution that merges YOLOv11, a popular deep learning based static object detector, with a custom designed lightweight motion-based segmentation model. This approach allows us to simultaneously capture fish dynamics and suppress background interference. The proposed model i.e., DeepFins attains 90.0% F1 Score for fish detection on the OzFish dataset (collected by the Australian Institute of Marine Science). To the best of our knowledge, these results are the most accurate yet, showing about 11% increase over the closest competitor in fish detection tasks on this demanding benchmark OzFish dataset. Moreover, DeepFins achieves an F1 Score of 83.7% on the Fish4Knowledge LifeCLEF 2015 dataset, marking an approximate 4% improvement over the baseline YOLOv11. This positions the proposed model as a highly practical solution for tasks like automated fish sampling and estimating their relative abundance.

{"title":"DeepFins: Capturing dynamics in underwater videos for fish detection","authors":"Ahsan Jalal , Ahmad Salman , Ajmal Mian , Salman Ghafoor , Faisal Shafait","doi":"10.1016/j.ecoinf.2025.103013","DOIUrl":"10.1016/j.ecoinf.2025.103013","url":null,"abstract":"<div><div>The monitoring of fish in their natural habitat plays a crucial role in anticipating changes within marine ecosystems. Marine scientists have a preference for automated, unrestricted underwater video-based sampling due to its non-invasive nature and its ability to yield desired outcomes more rapidly compared to manual sampling. Generally, research on automated video-based detection using computer vision and machine learning has been confined to controlled environments. Additionally, these solutions encounter difficulties when applied in real-world settings characterized by substantial environmental variability, including issues like poor visibility in unregulated underwater videos, challenges in capturing fish-related visual characteristics, and background interference. In response, we propose a hybrid solution that merges YOLOv11, a popular deep learning based static object detector, with a custom designed lightweight motion-based segmentation model. This approach allows us to simultaneously capture fish dynamics and suppress background interference. The proposed model i.e., DeepFins attains 90.0% F1 Score for fish detection on the OzFish dataset (collected by the Australian Institute of Marine Science). To the best of our knowledge, these results are the most accurate yet, showing about 11% increase over the closest competitor in fish detection tasks on this demanding benchmark OzFish dataset. Moreover, DeepFins achieves an F1 Score of 83.7% on the Fish4Knowledge LifeCLEF 2015 dataset, marking an approximate 4% improvement over the baseline YOLOv11. This positions the proposed model as a highly practical solution for tasks like automated fish sampling and estimating their relative abundance.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103013"},"PeriodicalIF":5.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0