Ecological Informatics最新文献_第4页

Using 360-degree panoramic technology to explore the mechanisms underlying the influence of landscape features on visual landscape quality in traditional villages

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-24 DOI: 10.1016/j.ecoinf.2025.103036

Huaheng Shen , Nor Fadzila Aziz , Xinyi Lv

Traditional villages, as integral components of cultures worldwide, preserve rich and irreplaceable tangible and intangible cultural heritage. However, due to China's rapid urbanization and the burgeoning rural tourism industry, the original landscape of traditional villages is being damaged. Therefore, their visual landscape quality must be scientifically evaluated and protected. This study explores the impact of landscape features on visual landscape quality. It considers Zhaoxing Dong and Basha Miao villages as case studies, utilizing 360-degree panoramic technology, a combination of scenic beauty estimation and semantic differential methods, and expert focus group discussions. The analyses revealed that eight landscape feature indicators significantly affect the visual landscape quality of traditional villages. Among these, landform diversity, waterscape, architectural style uniformity, historical sense of paved roads, folk activity landscape, and environmental cleanliness have a significant positive impact on visual landscape quality, whereas plant diversity and color richness exhibit complex bidirectional effects in enhancing visual landscape quality. Experts discussed the mechanisms underlying these influencing factors and proposed seven specific strategies and recommendations for protecting and enhancing the visual landscape quality of traditional villages: enhancing ecological aspects, preserving cultural heritage, improving infrastructure and environmental protection, encouraging community participation, developing relevant policies and regulations, promoting sustainable tourism development, and encouraging cross-sector cooperation with funding and technical support to ensure sustainable development.

{"title":"Using 360-degree panoramic technology to explore the mechanisms underlying the influence of landscape features on visual landscape quality in traditional villages","authors":"Huaheng Shen , Nor Fadzila Aziz , Xinyi Lv","doi":"10.1016/j.ecoinf.2025.103036","DOIUrl":"10.1016/j.ecoinf.2025.103036","url":null,"abstract":"<div><div>Traditional villages, as integral components of cultures worldwide, preserve rich and irreplaceable tangible and intangible cultural heritage. However, due to China's rapid urbanization and the burgeoning rural tourism industry, the original landscape of traditional villages is being damaged. Therefore, their visual landscape quality must be scientifically evaluated and protected. This study explores the impact of landscape features on visual landscape quality. It considers Zhaoxing Dong and Basha Miao villages as case studies, utilizing 360-degree panoramic technology, a combination of scenic beauty estimation and semantic differential methods, and expert focus group discussions. The analyses revealed that eight landscape feature indicators significantly affect the visual landscape quality of traditional villages. Among these, landform diversity, waterscape, architectural style uniformity, historical sense of paved roads, folk activity landscape, and environmental cleanliness have a significant positive impact on visual landscape quality, whereas plant diversity and color richness exhibit complex bidirectional effects in enhancing visual landscape quality. Experts discussed the mechanisms underlying these influencing factors and proposed seven specific strategies and recommendations for protecting and enhancing the visual landscape quality of traditional villages: enhancing ecological aspects, preserving cultural heritage, improving infrastructure and environmental protection, encouraging community participation, developing relevant policies and regulations, promoting sustainable tourism development, and encouraging cross-sector cooperation with funding and technical support to ensure sustainable development.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103036"},"PeriodicalIF":5.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102489","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

Correcting forest aboveground biomass biases by incorporating independent canopy height retrieval with conventional machine learning models using GEDI and ICESat-2 data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-24 DOI: 10.1016/j.ecoinf.2025.103045

Biao Zhang , Zhichao Wang , Tiantian Ma , Zhihao Wang , Hao Li , Wenxu Ji , Mingyang He , Ao Jiao , Zhongke Feng

Spaceborne LiDAR satellites, including GEDI and ICESat-2, have shown significant potential in estimating aboveground biomass (AGB) using machine learning (ML) methods. In contrast to advances focused on the refinement of ML algorithms, this study aims to enhance AGB estimation accuracy by integrating an additional Canopy Height (CH) information. To obtain CH data, this study utilized three spaceborne LiDAR datasets: ICESat-2 ATL08, ICESat-2 ATL03/ATL08 fusion data, and GEDI-L2A. Random Forest (RF) and Monte Carlo-based uncertainty analysis were employed to evaluate the most suitable spaceborne LiDAR dataset for CH estimation. The accuracy of CH features in AGB estimation was then compared using both Linear Regression (LR) and RF models. The spectral saturation point was computed using a semi-variance function, and the contribution of CH features to AGB estimates was quantified across different gradients, especially when AGB neared or surpassed the saturation point. The findings demonstrate that the ATL03/08 fusion dataset surpasses the other datasets in terms of CH estimation accuracy and uncertainty, delivering enhanced precision and stability. Incorporating CH features notably improved AGB model performance, as evidenced by R² increases of 13.89 % and 10.34 % in the LR and RF models, respectively. The correction of AGB estimates across various gradients with CH features demonstrated a nonlinear pattern, initially increasing, then decreasing, and subsequently rebounding. Notable inflection points were identified at 26 Mg/ha and 123 Mg/ha, marking significant transitions in the correction trend. Both positive and negative bias corrections were observed during the correction process, with their proportions varying according to AGB values. When AGB approached or exceeded the spectral saturation point, the ability of CH features to improve positive bias correction was markedly enhanced, resulting in a greater proportion of positively corrected pixels and more significant correction values. The results of this study provide new insights into the role of CH features in AGB estimation, offering important implications for enhancing biomass mapping accuracy in forest ecosystems.

{"title":"Correcting forest aboveground biomass biases by incorporating independent canopy height retrieval with conventional machine learning models using GEDI and ICESat-2 data","authors":"Biao Zhang , Zhichao Wang , Tiantian Ma , Zhihao Wang , Hao Li , Wenxu Ji , Mingyang He , Ao Jiao , Zhongke Feng","doi":"10.1016/j.ecoinf.2025.103045","DOIUrl":"10.1016/j.ecoinf.2025.103045","url":null,"abstract":"<div><div>Spaceborne LiDAR satellites, including GEDI and ICESat-2, have shown significant potential in estimating aboveground biomass (AGB) using machine learning (ML) methods. In contrast to advances focused on the refinement of ML algorithms, this study aims to enhance AGB estimation accuracy by integrating an additional Canopy Height (CH) information. To obtain CH data, this study utilized three spaceborne LiDAR datasets: ICESat-2 ATL08, ICESat-2 ATL03/ATL08 fusion data, and GEDI-L2A. Random Forest (RF) and Monte Carlo-based uncertainty analysis were employed to evaluate the most suitable spaceborne LiDAR dataset for CH estimation. The accuracy of CH features in AGB estimation was then compared using both Linear Regression (LR) and RF models. The spectral saturation point was computed using a semi-variance function, and the contribution of CH features to AGB estimates was quantified across different gradients, especially when AGB neared or surpassed the saturation point. The findings demonstrate that the ATL03/08 fusion dataset surpasses the other datasets in terms of CH estimation accuracy and uncertainty, delivering enhanced precision and stability. Incorporating CH features notably improved AGB model performance, as evidenced by R<sup>2</sup> increases of 13.89 % and 10.34 % in the LR and RF models, respectively. The correction of AGB estimates across various gradients with CH features demonstrated a nonlinear pattern, initially increasing, then decreasing, and subsequently rebounding. Notable inflection points were identified at 26 Mg/ha and 123 Mg/ha, marking significant transitions in the correction trend. Both positive and negative bias corrections were observed during the correction process, with their proportions varying according to AGB values. When AGB approached or exceeded the spectral saturation point, the ability of CH features to improve positive bias correction was markedly enhanced, resulting in a greater proportion of positively corrected pixels and more significant correction values. The results of this study provide new insights into the role of CH features in AGB estimation, offering important implications for enhancing biomass mapping accuracy in forest ecosystems.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103045"},"PeriodicalIF":5.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102128","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 fish (Coilia nasus) catch using spatiotemporal environmental variables and random forest model in a highly turbid macrotidal estuary

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-24 DOI: 10.1016/j.ecoinf.2025.103048

Vishal Singh Rawat, Gubash Azhikodan, Katsuhide Yokoyama

Fish populations in estuaries are declining due to the changes in environmental conditions and fishing pressures. The estuarine fish behaviour is highly variable, influenced by both upstream fluvial and downstream tidal conditions. This study aims to predict the catch per unit effort (CPUE) of the Japanese Grenadier Anchovy (Coilia nasus) in the Chikugo River estuary by analyzing an extensive dataset of hourly fish catches and environmental variables through Random Forest (RF) models. The fish catch data for C. nasus, collected at 14.6–16 km upstream from the river mouth during the spawning season of every year from 2009 to 2020 using traditional fishing methods, was used. Along with these catch records, hydro-environmental variables such as salinity, turbidity, and temperature were monitored during the same period. The longitudinal variation of these environmental variables along the estuary (0–16 km) was measured during a fortnightly tidal cycle in September 2010. A total of 32 models (M1-M32) were developed to identify the optimal set of environmental variables influencing CPUE. The analysis highlights the significant impact of variables such as salinity, suspended sediment concentration (SSC), temperature, river discharge, and mean tidal range on CPUE. The results revealed that model M19, which incorporated salinity, SSC, and discharge, achieved the highest predictive accuracy (R² = 0.89) and closely matched actual field conditions. Further, the results agree with previous research, as spatial distribution plots showed a preference for mature C. nasus habitats 15–16 km upstream from the river mouth. Additionally, the study found that temperature had a negligible effect on short-term CPUE predictions, likely due to its pronounced seasonal variability, suggesting that temperature may not be a critical factor for short-term CPUE predictions. This study highlights the significance of utilizing environmental variables to predict CPUE, emphasizing their role in understanding fish catch dynamics across spatiotemporal variations. The findings provide valuable insights for fisheries management, particularly in optimizing fishing zones based on environmental conditions to improve catch efficiency.

{"title":"Prediction of fish (Coilia nasus) catch using spatiotemporal environmental variables and random forest model in a highly turbid macrotidal estuary","authors":"Vishal Singh Rawat, Gubash Azhikodan, Katsuhide Yokoyama","doi":"10.1016/j.ecoinf.2025.103048","DOIUrl":"10.1016/j.ecoinf.2025.103048","url":null,"abstract":"<div><div>Fish populations in estuaries are declining due to the changes in environmental conditions and fishing pressures. The estuarine fish behaviour is highly variable, influenced by both upstream fluvial and downstream tidal conditions. This study aims to predict the catch per unit effort (CPUE) of the Japanese Grenadier Anchovy (<em>Coilia nasus</em>) in the Chikugo River estuary by analyzing an extensive dataset of hourly fish catches and environmental variables through Random Forest (RF) models. The fish catch data for <em>C. nasus</em>, collected at 14.6–16 km upstream from the river mouth during the spawning season of every year from 2009 to 2020 using traditional fishing methods, was used. Along with these catch records, hydro-environmental variables such as salinity, turbidity, and temperature were monitored during the same period. The longitudinal variation of these environmental variables along the estuary (0–16 km) was measured during a fortnightly tidal cycle in September 2010. A total of 32 models (M1-M32) were developed to identify the optimal set of environmental variables influencing CPUE. The analysis highlights the significant impact of variables such as salinity, suspended sediment concentration (SSC), temperature, river discharge, and mean tidal range on CPUE. The results revealed that model M19, which incorporated salinity, SSC, and discharge, achieved the highest predictive accuracy (R<sup>2</sup> = 0.89) and closely matched actual field conditions. Further, the results agree with previous research, as spatial distribution plots showed a preference for mature <em>C. nasus</em> habitats 15–16 km upstream from the river mouth. Additionally, the study found that temperature had a negligible effect on short-term CPUE predictions, likely due to its pronounced seasonal variability, suggesting that temperature may not be a critical factor for short-term CPUE predictions. This study highlights the significance of utilizing environmental variables to predict CPUE, emphasizing their role in understanding fish catch dynamics across spatiotemporal variations. The findings provide valuable insights for fisheries management, particularly in optimizing fishing zones based on environmental conditions to improve catch efficiency.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103048"},"PeriodicalIF":5.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102220","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

Assessing ecological connectivity in the Serra do Cando and Serra do Candán area of Galicia: A multitemporal classification and least-cost path modelling approach

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-24 DOI: 10.1016/j.ecoinf.2025.103049

Carlos Peco-Costas, Carolina Acuña-Alonso, Mario García-Ontiyuelo, Xana Álvarez

Ecological connectivity is essential for mitigating the anthropogenic impact caused by urbanization, infrastructure, and the production of goods on natural habitats and their fragmentation. This study assesses the state of ecological connectivity between hardwoods habitats in different years for a Natura 2000 area in Galicia, in northwestern Spain, the Serra do Cando and Candán. A supervised land cover classification was performed using two different machine learning algorithms, an Artificial Neural Network (ANN) and Random Forest (RF), and Sentinel-2 images from 2015 and 2022. A possible future land use scenario for the year 2029 was generated with Modules for Land Use Change Evaluation (MOLUSCE) plugin for QGIS from a Multilayer Perceptron ANN. Land use information was used to construct resistance surfaces on which ecological corridors were modelled as least-cost paths between habitat patches. The equivalent connected area (ECA) was calculated to quantify the level of connectivity and compare different time periods. Classifications achieved an accuracy of 91 % in RF and 88 % in ANN for the year 2015, and 92 % and 91 % respectively in 2022. The results for the year 2029 show a decrease in areas under crops and grassland according to RF and conifers in the case of ANN. The highest ECA values were reached in 2022 with 864 ha according to the RF-based methodology and 757 ha according to ANN. The area of hardwoods patches was the fundamental parameter that affects ECA. Combining remote sensing techniques with the least-cost paths method, including a simulation of future land use changes, has made it possible to compare the degree of ecological connectivity in different scenarios. This methodology shows the effects of land-cover changes and provides a tool to support decision making in land use planning.

{"title":"Assessing ecological connectivity in the Serra do Cando and Serra do Candán area of Galicia: A multitemporal classification and least-cost path modelling approach","authors":"Carlos Peco-Costas, Carolina Acuña-Alonso, Mario García-Ontiyuelo, Xana Álvarez","doi":"10.1016/j.ecoinf.2025.103049","DOIUrl":"10.1016/j.ecoinf.2025.103049","url":null,"abstract":"<div><div>Ecological connectivity is essential for mitigating the anthropogenic impact caused by urbanization, infrastructure, and the production of goods on natural habitats and their fragmentation. This study assesses the state of ecological connectivity between hardwoods habitats in different years for a Natura 2000 area in Galicia, in northwestern Spain, the Serra do Cando and Candán. A supervised land cover classification was performed using two different machine learning algorithms, an Artificial Neural Network (ANN) and Random Forest (RF), and Sentinel-2 images from 2015 and 2022. A possible future land use scenario for the year 2029 was generated with Modules for Land Use Change Evaluation (MOLUSCE) plugin for QGIS from a Multilayer Perceptron ANN. Land use information was used to construct resistance surfaces on which ecological corridors were modelled as least-cost paths between habitat patches. The equivalent connected area (ECA) was calculated to quantify the level of connectivity and compare different time periods. Classifications achieved an accuracy of 91 % in RF and 88 % in ANN for the year 2015, and 92 % and 91 % respectively in 2022. The results for the year 2029 show a decrease in areas under crops and grassland according to RF and conifers in the case of ANN. The highest ECA values were reached in 2022 with 864 ha according to the RF-based methodology and 757 ha according to ANN. The area of hardwoods patches was the fundamental parameter that affects ECA. Combining remote sensing techniques with the least-cost paths method, including a simulation of future land use changes, has made it possible to compare the degree of ecological connectivity in different scenarios. This methodology shows the effects of land-cover changes and provides a tool to support decision making in land use planning.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103049"},"PeriodicalIF":5.8,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102469","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 evaluation of vulnerability settings in Ecopath with Ecosim on ecosystem hindcast and forecast skills

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-23 DOI: 10.1016/j.ecoinf.2025.103040

Qingqiang Ren , Yuying Zhang , Jie Yin , Dongyan Han , Min Liu , Yong Chen

Ecological model fitting is a critical step in ensuring that models can reflect historical ecosystem dynamics, allowing for an improved understanding of ecological processes and potentially enhancing the reliability of future projections, despite inherent uncertainties. Vulnerability parameters (v), reflecting the predator-prey relationship, play a crucial role in the Ecopath with Ecosim (EwE) model fitting. However, many EwE applications have bypassed tuning the vulnerability parameters due to a lack of historical data, limiting the impacts of vulnerability-unfitted (v-unfitted) models on evaluating management strategies. In this study, we used model skill metrics, including bias, error, and reliability, to evaluate the hindcast and forecast skills of the v-unfitted models with multiple vulnerability settings. The prediction from vulnerability-fitted (v-fitted) model was found to have the best fitness and most accurately replicate historical ecosystem dynamics when compared to observed data. In addition, the v-unfitted model with trophic-level-related vulnerability setting (vTL) exhibited relatively better hindcast ability among the alternative v settings compared with v-fitted model. In terms of forecast skill under both reduced and increased fishing effort scenarios, only the depletion-related vulnerability setting (vB) was found to be robust for v-unfitted models comparing to v-fitted model predictions. We highlight the importance of examining various vulnerability settings, and providing a reference for the application of unfitted models in informing ecosystem-based fisheries management. Our results also reaffirm the critical role of time-series data in applying EwE models.

{"title":"An evaluation of vulnerability settings in Ecopath with Ecosim on ecosystem hindcast and forecast skills","authors":"Qingqiang Ren , Yuying Zhang , Jie Yin , Dongyan Han , Min Liu , Yong Chen","doi":"10.1016/j.ecoinf.2025.103040","DOIUrl":"10.1016/j.ecoinf.2025.103040","url":null,"abstract":"<div><div>Ecological model fitting is a critical step in ensuring that models can reflect historical ecosystem dynamics, allowing for an improved understanding of ecological processes and potentially enhancing the reliability of future projections, despite inherent uncertainties. Vulnerability parameters (<em>v</em>), reflecting the predator-prey relationship, play a crucial role in the Ecopath with Ecosim (EwE) model fitting. However, many EwE applications have bypassed tuning the vulnerability parameters due to a lack of historical data, limiting the impacts of vulnerability-unfitted (<em>v</em>-unfitted) models on evaluating management strategies. In this study, we used model skill metrics, including bias, error, and reliability, to evaluate the hindcast and forecast skills of the <em>v</em>-unfitted models with multiple vulnerability settings. The prediction from vulnerability-fitted (<em>v</em>-fitted) model was found to have the best fitness and most accurately replicate historical ecosystem dynamics when compared to observed data. In addition, the <em>v</em>-unfitted model with trophic-level-related vulnerability setting (<em>vTL</em>) exhibited relatively better hindcast ability among the alternative <em>v</em> settings compared with <em>v</em>-fitted model. In terms of forecast skill under both reduced and increased fishing effort scenarios, only the depletion-related vulnerability setting (<em>vB</em>) was found to be robust for <em>v</em>-unfitted models comparing to <em>v</em>-fitted model predictions. We highlight the importance of examining various vulnerability settings, and providing a reference for the application of unfitted models in informing ecosystem-based fisheries management. Our results also reaffirm the critical role of time-series data in applying EwE models.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103040"},"PeriodicalIF":5.8,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102082","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

Beekeeping suitability prediction based on an adaptive neuro-fuzzy inference system and apiary level data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-23 DOI: 10.1016/j.ecoinf.2025.103015

Guy A. Fotso Kamga , Yacine Bouroubi , Mickaël Germain , Georges Martin , Laurent Bitjoka

The study employs a predictive modelling approach using a fuzzy inference system to assess the beekeeping potential of a geographic area. Specifically, an adaptive neuro-fuzzy inference system with subtractive clustering (ANFIS-SC) was utilized, incorporating six input variables that influence Apis mellifera health and productivity, and field data as the output variable reflecting the state of a colony. The results demonstrate the model’s effectiveness in predicting the suitability of areas for beekeeping. Sensitivity analysis highlighted the significant effects of relative humidity on the model’s output. The research underscores the importance of data quality, particularly in determining the local land cover quality index (LLCQI), on the outcomes. This study highlights the role of data science in enhancing precision in beekeeping and proposes its integration into management practices to support honey bee health.

引用次数: 0

A comprehensive evaluation of deep learning approaches for ground-level ozone prediction across different regions

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-23 DOI: 10.1016/j.ecoinf.2025.103024

Guanjun Lin , Hang Zhao , Yufeng Chi

<div><div>Recently, the issue of near-surface ozone pollution has become a growing concern. To effectively manage and control ozone pollution, emerging deep learning (DL) techniques have been applied for future ozone concentration trend prediction, generating promising outcomes. However, existing studies employ various DL models and rely on diverse datasets to predict ozone concentrations. This leads to a lack of comprehensive evaluations of how the architecture and depth of different DL models influence the predictive accuracy of ozone concentration trends when assessed using a unified dataset. This lack of uniformity in evaluations creates a gap in our understanding of the influence of different neural network architectures and depths on ozone concentration predictions. In this work, we aim to address this research gap by conducting a systematic performance evaluation that benchmarks six prominent DL architectures, each with varying depths, to evaluate their effectiveness for predicting ozone concentrations across diverse geographical regions. Our findings indicate that the best-performing DL model in the nationwide prediction task is the one-layer bidirectional long short-term memory (Bi-LSTM) model, which achieves an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.66, an RMSE of 15.32<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>, and an MAE of 11.51<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>. In contrast, the poorest-performing model in the same prediction task is the one-block transformer-based model, with an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.57, an RMSE of 17.34<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>, and an MAE of 13.3<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>. Furthermore, fully connected networks (FCNs) demonstrate robust and efficient predictive performance across both nationwide and regional prediction tasks. Notably, our study reveals that no single DL model consistently performs well across all prediction tasks, emphasizing the need for tailored approaches that cater to the specific attributes of each region. Additionally, we observe that DL models with more than two hidden layers frequently suffer from overfitting. Particularly for the Bi-LSTM architecture, as the number of hidden layers increases from 1 to 7, we observe a 12% reduction in <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> performance. Our analysis also identifies the most influential meteorological factors among the top-performing DL models, offering insigh

{"title":"A comprehensive evaluation of deep learning approaches for ground-level ozone prediction across different regions","authors":"Guanjun Lin , Hang Zhao , Yufeng Chi","doi":"10.1016/j.ecoinf.2025.103024","DOIUrl":"10.1016/j.ecoinf.2025.103024","url":null,"abstract":"<div><div>Recently, the issue of near-surface ozone pollution has become a growing concern. To effectively manage and control ozone pollution, emerging deep learning (DL) techniques have been applied for future ozone concentration trend prediction, generating promising outcomes. However, existing studies employ various DL models and rely on diverse datasets to predict ozone concentrations. This leads to a lack of comprehensive evaluations of how the architecture and depth of different DL models influence the predictive accuracy of ozone concentration trends when assessed using a unified dataset. This lack of uniformity in evaluations creates a gap in our understanding of the influence of different neural network architectures and depths on ozone concentration predictions. In this work, we aim to address this research gap by conducting a systematic performance evaluation that benchmarks six prominent DL architectures, each with varying depths, to evaluate their effectiveness for predicting ozone concentrations across diverse geographical regions. Our findings indicate that the best-performing DL model in the nationwide prediction task is the one-layer bidirectional long short-term memory (Bi-LSTM) model, which achieves an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.66, an RMSE of 15.32<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>, and an MAE of 11.51<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>. In contrast, the poorest-performing model in the same prediction task is the one-block transformer-based model, with an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.57, an RMSE of 17.34<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>, and an MAE of 13.3<span><math><mrow><mi>μ</mi><mi>g</mi><mi>⋅</mi><msup><mrow><mi>m</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>. Furthermore, fully connected networks (FCNs) demonstrate robust and efficient predictive performance across both nationwide and regional prediction tasks. Notably, our study reveals that no single DL model consistently performs well across all prediction tasks, emphasizing the need for tailored approaches that cater to the specific attributes of each region. Additionally, we observe that DL models with more than two hidden layers frequently suffer from overfitting. Particularly for the Bi-LSTM architecture, as the number of hidden layers increases from 1 to 7, we observe a 12% reduction in <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> performance. Our analysis also identifies the most influential meteorological factors among the top-performing DL models, offering insigh","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103024"},"PeriodicalIF":5.8,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101990","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

Surveying the deep: A review of computer vision in the benthos

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-22 DOI: 10.1016/j.ecoinf.2024.102989

Cameron Trotter, Huw J. Griffiths, Rowan J. Whittle

The analysis of image data for benthic biodiversity monitoring is now commonplace within the domain of marine ecology. Whilst advances in imaging technologies have allowed for the collection of vast quantities of data, the curation of this has traditionally been performed manually, resulting in a bottleneck whereby data is collected faster than it can be processed. Recent years have seen marine ecologists turn to the domain of computer vision to help automate this curation process. However, as the knowledge required to build such systems spans both domains, there is a high barrier to entry. To help reduce this barrier, this paper aims to provide an introduction to computer vision-based benthic biodiversity monitoring via a comprehensive literature review. To aid ecologists, key computer vision concepts are described and example use-cases highlighted. The major challenges inherent to benthic imagery for computer vision systems are explored, alongside a discussion of how current systems attempt to mitigate against these. To aid computer scientists wishing to enter the domain, an exploration of currently available open-source benthic datasets is also provided. Recommendations for future research are explored, including a move towards human-centric techniques, committing to ablation studies, reaching community agreement on open-source benchmarking datasets, and an increased use of innovative methods to allow for improved answering of key benthic ecology questions.

{"title":"Surveying the deep: A review of computer vision in the benthos","authors":"Cameron Trotter, Huw J. Griffiths, Rowan J. Whittle","doi":"10.1016/j.ecoinf.2024.102989","DOIUrl":"10.1016/j.ecoinf.2024.102989","url":null,"abstract":"<div><div>The analysis of image data for benthic biodiversity monitoring is now commonplace within the domain of marine ecology. Whilst advances in imaging technologies have allowed for the collection of vast quantities of data, the curation of this has traditionally been performed manually, resulting in a bottleneck whereby data is collected faster than it can be processed. Recent years have seen marine ecologists turn to the domain of computer vision to help automate this curation process. However, as the knowledge required to build such systems spans both domains, there is a high barrier to entry. To help reduce this barrier, this paper aims to provide an introduction to computer vision-based benthic biodiversity monitoring via a comprehensive literature review. To aid ecologists, key computer vision concepts are described and example use-cases highlighted. The major challenges inherent to benthic imagery for computer vision systems are explored, alongside a discussion of how current systems attempt to mitigate against these. To aid computer scientists wishing to enter the domain, an exploration of currently available open-source benthic datasets is also provided. Recommendations for future research are explored, including a move towards human-centric techniques, committing to ablation studies, reaching community agreement on open-source benchmarking datasets, and an increased use of innovative methods to allow for improved answering of key benthic ecology questions.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102989"},"PeriodicalIF":5.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101993","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

Transformer Models improve the acoustic recognition of buzz-pollinating bee species

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-22 DOI: 10.1016/j.ecoinf.2025.103010

Alef Iury Siqueira Ferreira , Nádia Felix Felipe da Silva , Fernanda Neiva Mesquita , Thierson Couto Rosa , Stephen L. Buchmann , José Neiva Mesquita-Neto

Buzz-pollinated crops, such as tomatoes, potatoes, kiwifruit, and blueberries, are among the highest-yielding agricultural products. The flowers of these cultivated plants are characterized by having a specialized flower morphology with poricidal anthers that require vibration to achieve a full seed set. At least 446 bee species, in 82 genera, use floral sonication (buzz pollination) to collect pollen grains as food. Identifying and classifying these diverse often look-alike bee species poses a challenge for taxonomists. Automated classification systems, based upon audible bee floral buzzes, have been investigated to meet this need. Recently, convolutional neural network (CNN) models have demonstrated superior performance in recognizing and distinguishing bee-buzzing sounds compared to classical Machine-Learning (ML) classifiers. Nonetheless, the performance of CNNs remains unsatisfactory and can be improved. Therefore, we applied a novel transformer-based neural network architecture for the task of acoustic recognition of blueberry-pollinating bee species. We further compared the performance of the Audio Spectrogram Transformer (AST) model and its variants, including Self-Supervised AST (SSAST) and Masked Autoencoding AST (MAE-AST), to that of strong baseline CNN models based on previous work, at the task of bee species recognition. We also employed data augmentation techniques and evaluated these models with a data set of bee sounds recorded during visits to blueberry flowers in Chile (518 audio samples of 15 bee species). Our results revealed that Transformer-based Neural Networks combined with pre-training and data augmentation outperformed CNN models (maximum F1-score: 64.5% ± 2; Accuracy: 82.2% ± 0.8). These innovative attention-based neural network architectures have demonstrated exceptional performance in assigning bee buzzing sounds to their respective taxonomic categories, outperforming prior deep learning models. However, transformer approaches face challenges related to small dataset size and class imbalance, similar to CNNs and classical ML algorithms. Combining pre-training with data augmentation is crucial to increase the diversity and robustness of training data sets for the acoustic recognition of bee species. We document the potential of transformer architectures to improve the performance of audible bee species identification, offering promising new avenues for bioacoustic research and pollination ecology.

{"title":"Transformer Models improve the acoustic recognition of buzz-pollinating bee species","authors":"Alef Iury Siqueira Ferreira , Nádia Felix Felipe da Silva , Fernanda Neiva Mesquita , Thierson Couto Rosa , Stephen L. Buchmann , José Neiva Mesquita-Neto","doi":"10.1016/j.ecoinf.2025.103010","DOIUrl":"10.1016/j.ecoinf.2025.103010","url":null,"abstract":"<div><div>Buzz-pollinated crops, such as tomatoes, potatoes, kiwifruit, and blueberries, are among the highest-yielding agricultural products. The flowers of these cultivated plants are characterized by having a specialized flower morphology with poricidal anthers that require vibration to achieve a full seed set. At least 446 bee species, in 82 genera, use floral sonication (buzz pollination) to collect pollen grains as food. Identifying and classifying these diverse often look-alike bee species poses a challenge for taxonomists. Automated classification systems, based upon audible bee floral buzzes, have been investigated to meet this need. Recently, convolutional neural network (CNN) models have demonstrated superior performance in recognizing and distinguishing bee-buzzing sounds compared to classical Machine-Learning (ML) classifiers. Nonetheless, the performance of CNNs remains unsatisfactory and can be improved. Therefore, we applied a novel transformer-based neural network architecture for the task of acoustic recognition of blueberry-pollinating bee species. We further compared the performance of the Audio Spectrogram Transformer (AST) model and its variants, including Self-Supervised AST (SSAST) and Masked Autoencoding AST (MAE-AST), to that of strong baseline CNN models based on previous work, at the task of bee species recognition. We also employed data augmentation techniques and evaluated these models with a data set of bee sounds recorded during visits to blueberry flowers in Chile (518 audio samples of 15 bee species). Our results revealed that Transformer-based Neural Networks combined with pre-training and data augmentation outperformed CNN models (maximum F1-score: 64.5% ± 2; Accuracy: 82.2% ± 0.8). These innovative attention-based neural network architectures have demonstrated exceptional performance in assigning bee buzzing sounds to their respective taxonomic categories, outperforming prior deep learning models. However, transformer approaches face challenges related to small dataset size and class imbalance, similar to CNNs and classical ML algorithms. Combining pre-training with data augmentation is crucial to increase the diversity and robustness of training data sets for the acoustic recognition of bee species. We document the potential of transformer architectures to improve the performance of audible bee species identification, offering promising new avenues for bioacoustic research and pollination ecology.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103010"},"PeriodicalIF":5.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101994","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

Identifying sources of dissolved organic matter in sediments of a shallow lake by fluorescence and ultraviolet spectral characteristics of water and alkali extractable organic matter (WEOM and AEOM)

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2025-01-22 DOI: 10.1016/j.ecoinf.2025.103043

Jun Cao , Tianyu Chen , Jipeng Sun , Jun Zhong , Biao Mu , Xin Wang , Chunyan Wang , Massimiliano Materazzi , Hualun Zhu

This study investigates the potential of fluorescence characteristics of dissolved organic matter (DOM) to identify sediment organic matter (OM) sources in shallow lakes. Spectral analyses were performed on water and alkali extractable organic matter (WEOM and AEOM) from Lake Taihu sediments. The lake was divided into seven distinct regions: R1 and R2 strongly influenced by inflowing rivers, R3 and R4 were characterized by submerged macrophytes, and R5-R7 were dominated by cyanobacterial blooms. The investigation illustrated that the highest values of water and alkali extractable organic carbon (WEOC and AEOC) were found in region R4. Specifically, the Humification Index (HIX) values consistently exceeded 2.0 in the northwest regions, contrasting with values predominantly below 1.0 in most southeastern regions. Moreover, the Fluorescence Index (FI) of WEOM in regions R5, R6 and R7 reached 2.10, markedly higher than the values observed in other regions. The horizontal distribution of the four spectrographic indices of AEOM exhibited partial similarity to the distribution pattern of WEOM. Although the WEOC content marginally trailed AEOC, there was a significant correlation between WEOM and AEOM in three indices including slope ratio (S_R), HIX and FI. The identification of sources implied that organic matter in sediments of regions R1 and R2 originated from terrestrial sources, while regions R3 and R4 were largely derived from submerged macrophyte and the regions R5-R7 were notably impacted by cyanobacteria-derived organic matters. Notably, the identification results aligned perfectly with the distribution of inflowing rivers, cyanobacterial blooms and submerged macrophyte coverage within Taihu Lake, underscoring the potential use of dissolved organic matter's spectral characteristics for organic matter source analysis within sediments.

Synopsis

This study identifies distinct sources and spatial distributions of organic matter in Lake Taihu's sediments, using fluorescence characteristics to highlight influences from terrestrial input, submerged macrophytes, and cyanobacterial blooms.

{"title":"Identifying sources of dissolved organic matter in sediments of a shallow lake by fluorescence and ultraviolet spectral characteristics of water and alkali extractable organic matter (WEOM and AEOM)","authors":"Jun Cao , Tianyu Chen , Jipeng Sun , Jun Zhong , Biao Mu , Xin Wang , Chunyan Wang , Massimiliano Materazzi , Hualun Zhu","doi":"10.1016/j.ecoinf.2025.103043","DOIUrl":"10.1016/j.ecoinf.2025.103043","url":null,"abstract":"<div><div>This study investigates the potential of fluorescence characteristics of dissolved organic matter (DOM) to identify sediment organic matter (OM) sources in shallow lakes. Spectral analyses were performed on water and alkali extractable organic matter (WEOM and AEOM) from Lake Taihu sediments. The lake was divided into seven distinct regions: R1 and R2 strongly influenced by inflowing rivers, R3 and R4 were characterized by submerged macrophytes, and R5-R7 were dominated by cyanobacterial blooms. The investigation illustrated that the highest values of water and alkali extractable organic carbon (WEOC and AEOC) were found in region R4. Specifically, the Humification Index (HIX) values consistently exceeded 2.0 in the northwest regions, contrasting with values predominantly below 1.0 in most southeastern regions. Moreover, the Fluorescence Index (FI) of WEOM in regions R5, R6 and R7 reached 2.10, markedly higher than the values observed in other regions. The horizontal distribution of the four spectrographic indices of AEOM exhibited partial similarity to the distribution pattern of WEOM. Although the WEOC content marginally trailed AEOC, there was a significant correlation between WEOM and AEOM in three indices including slope ratio (S<sub>R</sub>), HIX and FI. The identification of sources implied that organic matter in sediments of regions R1 and R2 originated from terrestrial sources, while regions R3 and R4 were largely derived from submerged macrophyte and the regions R5-R7 were notably impacted by cyanobacteria-derived organic matters. Notably, the identification results aligned perfectly with the distribution of inflowing rivers, cyanobacterial blooms and submerged macrophyte coverage within Taihu Lake, underscoring the potential use of dissolved organic matter's spectral characteristics for organic matter source analysis within sediments.</div></div><div><h3>Synopsis</h3><div>This study identifies distinct sources and spatial distributions of organic matter in Lake Taihu's sediments, using fluorescence characteristics to highlight influences from terrestrial input, submerged macrophytes, and cyanobacterial blooms.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 103043"},"PeriodicalIF":5.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102486","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