Ecological Informatics最新文献_第10页

The dynamic driving mechanisms of wetland change from an asynchrony-spatiotemporal perspective: A case study in Pearl River Delta, China

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-28 DOI: 10.1016/j.ecoinf.2024.102979

Xiaoqing Yi , Yuhang Wang , Changjun Gao , Jiaojiao Ma , Demin Zhou , Christian J. Sanders , Guangjia Jiang , Zhongwen Hu , Junjie Wang , Haichao Zhou , Wei Li

The mechanism of wetland distribution (WD) has been well studied, but further research is needed on the mechanism of wetland change (WC). This study developed a model of the impact of changes in human activity (HA) and natural environment factors on WC from an asynchronous–spatiotemporal perspective, integrating remote sensing technologies and partial least squares–structural equation modeling (PLS–SEM). In the model, HA was reflected by economic and population data. The natural environment was reflected by the fundamental natural environment (FNE), which was mainly based on terrain, and the non-stable natural environment (NNE), which was mainly based on hydrological and temperature conditions. The model met the accuracy requirements in the Pearl River Delta (PRD). The results showed that there were differences in the response of WD and WC to driving factors from 1980 to 2020 in the PRD. FNE had a negative impact on WD, however, FNE changes (FNEC) had a positive impact on WC (mainly wetlands decrease). HA could affect NNE and subsequently WD, but NNE changes (NNEC) only began to affect WC after 2010. HA had a negative impact on WD and WC from 1980 to 2010, but both negative and positive impacts existed after 2010. By coupling areas of HA changes (HAC) with wetland decrease, it was found that HA should be restricted in the southeast of Foshan (areas where HA increase led to wetland decrease) to protect wetlands; The junction between Zhaoqing and Foshan (areas where HA decrease lead to wetland decrease) requires investment in improving the natural environment. The model proposed in this study can be applied to other areas with severe wetland degradation from HA and natural conditions, to assist in local wetland restoration and management.

{"title":"The dynamic driving mechanisms of wetland change from an asynchrony-spatiotemporal perspective: A case study in Pearl River Delta, China","authors":"Xiaoqing Yi , Yuhang Wang , Changjun Gao , Jiaojiao Ma , Demin Zhou , Christian J. Sanders , Guangjia Jiang , Zhongwen Hu , Junjie Wang , Haichao Zhou , Wei Li","doi":"10.1016/j.ecoinf.2024.102979","DOIUrl":"10.1016/j.ecoinf.2024.102979","url":null,"abstract":"<div><div>The mechanism of wetland distribution (WD) has been well studied, but further research is needed on the mechanism of wetland change (WC). This study developed a model of the impact of changes in human activity (HA) and natural environment factors on WC from an asynchronous–spatiotemporal perspective, integrating remote sensing technologies and partial least squares–structural equation modeling (PLS–SEM). In the model, HA was reflected by economic and population data. The natural environment was reflected by the fundamental natural environment (FNE), which was mainly based on terrain, and the non-stable natural environment (NNE), which was mainly based on hydrological and temperature conditions. The model met the accuracy requirements in the Pearl River Delta (PRD). The results showed that there were differences in the response of WD and WC to driving factors from 1980 to 2020 in the PRD. FNE had a negative impact on WD, however, FNE changes (FNEC) had a positive impact on WC (mainly wetlands decrease). HA could affect NNE and subsequently WD, but NNE changes (NNEC) only began to affect WC after 2010. HA had a negative impact on WD and WC from 1980 to 2010, but both negative and positive impacts existed after 2010. By coupling areas of HA changes (HAC) with wetland decrease, it was found that HA should be restricted in the southeast of Foshan (areas where HA increase led to wetland decrease) to protect wetlands; The junction between Zhaoqing and Foshan (areas where HA decrease lead to wetland decrease) requires investment in improving the natural environment. The model proposed in this study can be applied to other areas with severe wetland degradation from HA and natural conditions, to assist in local wetland restoration and management.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102979"},"PeriodicalIF":5.8,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101817","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

Digital mapping of soil salinity with time-windows features optimization and ensemble learning model

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-27 DOI: 10.1016/j.ecoinf.2024.102982

Shuaishuai Shi , Nan Wang , Songchao Chen , Bifeng Hu , Jie Peng , Zhou Shi

Soil salinization poses considerable global environmental and ecological risks. Remote-sensing time-series data enable more accurate monitoring and prediction of soil salinity levels, offering a refined approach to soil salinization assessment. However, the current limitations of time-series data analysis—particularly in terms of timely and effective information extraction—hinder high-precision soil salinity assessments. This study proposes a data mining approach using Sentinel-1 time-series data, integrating time-series decomposition and feature selection to capture seasonal and trend components correlated with soil salinity, and determine optimal time windows and effective time spans. An advanced feature-selection algorithm was then applied to refine the model-relevant features, and the transferability of the method across different regions was validated through empirical testing. The results revealed a 12 month periodicity in the correlation between Sentinel-1 time-series features and soil salinity, with an annual decay rate of 0.0019. In the study area, the optimal time window was from July to September, with the maximum effective years ranging from 19 to 21. Recursive feature elimination has shown a gradually increasing trend in the importance of SAR features from single-temporal to multi-temporal to time-series data. The time-series analysis combined with feature selection not only significantly reduced data volumes, but also improved the prediction accuracy of the model—increased R² of the prediction set was improved by 0.11, and a reduced root mean square error of 3.08 g kg⁻¹, compared to single-temporal data. Furthermore, the results demonstrate that the ensemble model outperforms the individual models in terms of inversion accuracy, whereas the time-series mining method exhibits generalizability across diverse study areas and metrics. The combination of the time-series mining method with the ensemble model helps achieve a higher accuracy in digital soil mapping.

{"title":"Digital mapping of soil salinity with time-windows features optimization and ensemble learning model","authors":"Shuaishuai Shi , Nan Wang , Songchao Chen , Bifeng Hu , Jie Peng , Zhou Shi","doi":"10.1016/j.ecoinf.2024.102982","DOIUrl":"10.1016/j.ecoinf.2024.102982","url":null,"abstract":"<div><div>Soil salinization poses considerable global environmental and ecological risks. Remote-sensing time-series data enable more accurate monitoring and prediction of soil salinity levels, offering a refined approach to soil salinization assessment. However, the current limitations of time-series data analysis—particularly in terms of timely and effective information extraction—hinder high-precision soil salinity assessments. This study proposes a data mining approach using Sentinel-1 time-series data, integrating time-series decomposition and feature selection to capture seasonal and trend components correlated with soil salinity, and determine optimal time windows and effective time spans. An advanced feature-selection algorithm was then applied to refine the model-relevant features, and the transferability of the method across different regions was validated through empirical testing. The results revealed a 12 month periodicity in the correlation between Sentinel-1 time-series features and soil salinity, with an annual decay rate of 0.0019. In the study area, the optimal time window was from July to September, with the maximum effective years ranging from 19 to 21. Recursive feature elimination has shown a gradually increasing trend in the importance of SAR features from single-temporal to multi-temporal to time-series data. The time-series analysis combined with feature selection not only significantly reduced data volumes, but also improved the prediction accuracy of the model—increased R<sup>2</sup> of the prediction set was improved by 0.11, and a reduced root mean square error of 3.08 g kg<sup>−1</sup>, compared to single-temporal data. Furthermore, the results demonstrate that the ensemble model outperforms the individual models in terms of inversion accuracy, whereas the time-series mining method exhibits generalizability across diverse study areas and metrics. The combination of the time-series mining method with the ensemble model helps achieve a higher accuracy in digital soil mapping.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102982"},"PeriodicalIF":5.8,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137559","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

This is EPIC: Extensive Periphery for Impact and Control to study seabird habitat loss in and around offshore wind farms combining a peripheral control area and Bayesian statistics

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-25 DOI: 10.1016/j.ecoinf.2024.102981

Anne Grundlehner , Mardik F. Leopold , Anna Kersten

With the rapidly increasing intensity of human activities in the marine realm, it has become urgent to better understand the impacts of human-induced disturbances on marine species. Marine mammals and birds are often observed to alter their fine-scale spatial distribution patterns in the presence of human at-sea activities, such as ship traffic and offshore wind farms (OWFs). This study presents EPIC (Extensive Periphery for Impact and Control), a novel approach for investigating such displacement in marine megafauna. The approach consists of a survey design that uses the OWFs surroundings in all directions as control space, complemented by a sophisticated statistical approach to quantify the extent and intensity of displacement and habitat loss in and around the area of potential disturbance. The approach is showcased by investigating the effects of an OWF in the Dutch North Sea on the habitat use of razorbills (Alca torda) and common guillemots (Uria aalge), two seabird species that occur in large numbers across the North Sea. We used an explicit spatial-temporal Bayesian model to predict their spatial distribution patterns based on eight aerial surveysed. The model output is used for a simulation study, comparing bird densities in the potential impact area with 1000 similarly sized control areas from the peripheral control space and from these, displacement around the OWF. Strong displacement was found for both razorbills and guillemots, within the OWF footprint but also in its surroundings. Razorbill and guillemot densities inside the OWF were reduced by 0.953 and 1.604 individuals per km², respectively, compared to the remainder of the study area, remaining considerably lower than control densities up to 2 km and > 10 km distance. The presented methodological approach holds great potential for future studies on the effects of local disturbances on displacement of marine megafauna.

{"title":"This is EPIC: Extensive Periphery for Impact and Control to study seabird habitat loss in and around offshore wind farms combining a peripheral control area and Bayesian statistics","authors":"Anne Grundlehner , Mardik F. Leopold , Anna Kersten","doi":"10.1016/j.ecoinf.2024.102981","DOIUrl":"10.1016/j.ecoinf.2024.102981","url":null,"abstract":"<div><div>With the rapidly increasing intensity of human activities in the marine realm, it has become urgent to better understand the impacts of human-induced disturbances on marine species. Marine mammals and birds are often observed to alter their fine-scale spatial distribution patterns in the presence of human at-sea activities, such as ship traffic and offshore wind farms (OWFs). This study presents EPIC (Extensive Periphery for Impact and Control), a novel approach for investigating such displacement in marine megafauna. The approach consists of a survey design that uses the OWFs surroundings in all directions as control space, complemented by a sophisticated statistical approach to quantify the extent and intensity of displacement and habitat loss in and around the area of potential disturbance. The approach is showcased by investigating the effects of an OWF in the Dutch North Sea on the habitat use of razorbills (<em>Alca torda</em>) and common guillemots (<em>Uria aalge</em>), two seabird species that occur in large numbers across the North Sea. We used an explicit spatial-temporal Bayesian model to predict their spatial distribution patterns based on eight aerial surveysed. The model output is used for a simulation study, comparing bird densities in the potential impact area with 1000 similarly sized control areas from the peripheral control space and from these, displacement around the OWF. Strong displacement was found for both razorbills and guillemots, within the OWF footprint but also in its surroundings. Razorbill and guillemot densities inside the OWF were reduced by 0.953 and 1.604 individuals per km<sup>2</sup>, respectively, compared to the remainder of the study area, remaining considerably lower than control densities up to 2 km and > 10 km distance. The presented methodological approach holds great potential for future studies on the effects of local disturbances on displacement of marine megafauna.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102981"},"PeriodicalIF":5.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137490","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

Random forest model that incorporates solar-induced chlorophyll fluorescence data can accurately track crop yield variations under drought conditions

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-24 DOI: 10.1016/j.ecoinf.2024.102972

Guangpo Geng , Qian Gu , Hongkui Zhou , Bao Zhang , Zuxin He , Ruolin Zheng

Timely and reliable crop yield estimation is vital for ensuring both global and regional food security. Previous studies have primarily used process-based crop models or statistical regression-based models for crop yield estimates. However, these model types possess limitations, particularly in accounting for specific extreme climate events that occur during the growth stage. In this study, remote sensing data, climate data, and soil moisture data from the winter wheat growth period in northern China from 2003 to 2017 were used to construct a crop yield simulation model based on the Random Forest (RF) algorithm. The effect of drought on winter wheat yield was quantitatively evaluated by calculating the fitting accuracy of the RF model, analyzing the importance of the factors influencing yield simulations, identifying a typical drought event, and determining the yield estimation accuracy as well as the percent yield loss (PYL) under drought conditions. The results indicated that solar-induced chlorophyll fluorescence (SIF) could characterize drought stress on winter wheat yield. The fitting accuracy of the RF yield simulation model was relatively high (R² = 0.72). Among all climate factors, SIF, enhanced vegetation index, and soil moisture were significant factors affecting wheat yield, exerting greater effect than those of all other climate factors. Furthermore, 2011 was identified as a typical drought year in the winter wheat area of northern China. The RF model simulated the accuracy of winter wheat yield for 2011 with an R² of 0.80. The RF model simulation revealed that the yield simulation accuracy of winter wheat under drought conditions was 90.64 %. The mean simulated PYL due to drought was 5.6 %, aligning closely with the mean actual PYL of 6.1 %. This suggested that the RF model was feasible for simulating crop yields and tracking yield variations by incorporating environmental variables, especially SIF data, under drought conditions.

{"title":"Random forest model that incorporates solar-induced chlorophyll fluorescence data can accurately track crop yield variations under drought conditions","authors":"Guangpo Geng , Qian Gu , Hongkui Zhou , Bao Zhang , Zuxin He , Ruolin Zheng","doi":"10.1016/j.ecoinf.2024.102972","DOIUrl":"10.1016/j.ecoinf.2024.102972","url":null,"abstract":"<div><div>Timely and reliable crop yield estimation is vital for ensuring both global and regional food security. Previous studies have primarily used process-based crop models or statistical regression-based models for crop yield estimates. However, these model types possess limitations, particularly in accounting for specific extreme climate events that occur during the growth stage. In this study, remote sensing data, climate data, and soil moisture data from the winter wheat growth period in northern China from 2003 to 2017 were used to construct a crop yield simulation model based on the Random Forest (RF) algorithm. The effect of drought on winter wheat yield was quantitatively evaluated by calculating the fitting accuracy of the RF model, analyzing the importance of the factors influencing yield simulations, identifying a typical drought event, and determining the yield estimation accuracy as well as the percent yield loss (PYL) under drought conditions. The results indicated that solar-induced chlorophyll fluorescence (SIF) could characterize drought stress on winter wheat yield. The fitting accuracy of the RF yield simulation model was relatively high (R<sup>2</sup> = 0.72). Among all climate factors, SIF, enhanced vegetation index, and soil moisture were significant factors affecting wheat yield, exerting greater effect than those of all other climate factors. Furthermore, 2011 was identified as a typical drought year in the winter wheat area of northern China. The RF model simulated the accuracy of winter wheat yield for 2011 with an R<sup>2</sup> of 0.80. The RF model simulation revealed that the yield simulation accuracy of winter wheat under drought conditions was 90.64 %. The mean simulated PYL due to drought was 5.6 %, aligning closely with the mean actual PYL of 6.1 %. This suggested that the RF model was feasible for simulating crop yields and tracking yield variations by incorporating environmental variables, especially SIF data, under drought conditions.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102972"},"PeriodicalIF":5.8,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137036","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

Modelling height to crown base using non-parametric methods for mixed forests in China

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-24 DOI: 10.1016/j.ecoinf.2024.102957

Zeyu Zhou , Huiru Zhang , Ram P. Sharma , Xiaohong Zhang , Linyan Feng , Manyi Du , Lianjin Zhang , Huanying Feng , Xuefan Hu , Yang Yu

The height to crown base (HCB) of a tree is a vital characteristic that reflects the self-thinning ability of a tree, and it is used to determine the crown size. and predict the crown recession rate. This study simulated the HCB of Spruce fir broadleaved mixed forest in Northeast China using four non-parametric model approaches: generalized additive model, Cubist, boosted regression tree (BRT), and multiple adaptive regression spline. Because of the different genetic characteristics and growth patterns of different tree species, species-specific tree groups were formed, and the HCB of each species-specific group was simulated by the different models. Relative importance and partial dependence analyses were performed to identify the primary HCB predictors (including tree, stand, stand spatial structure, density and competition factors) and their relationships with the HCB of the four tree species groups. The relative importance was higher for individual tree variables (77.54 %, 31.02 %, 31.12 %, and 73.69 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively) and stand variables (5.00 %, 20.34 %, 11.03 %, and 8.71 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively) compared with stand spatial structure variables (4.57 %, 12.14 %, 21.91 %, and 5.89 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively), density indexes variables (2.17 %, 1.28 %, 4.05 %, and 2.87 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively), and tree species variables (10.79 %, 35.20 %, 31.90 %, and 8.84 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively). BRT and Cubist were the best approaches for modelling the four species-group specific HCBs. Although spatial structure variables had minor relative importance, further in-depth investigations are warranted.

{"title":"Modelling height to crown base using non-parametric methods for mixed forests in China","authors":"Zeyu Zhou , Huiru Zhang , Ram P. Sharma , Xiaohong Zhang , Linyan Feng , Manyi Du , Lianjin Zhang , Huanying Feng , Xuefan Hu , Yang Yu","doi":"10.1016/j.ecoinf.2024.102957","DOIUrl":"10.1016/j.ecoinf.2024.102957","url":null,"abstract":"<div><div>The height to crown base (HCB) of a tree is a vital characteristic that reflects the self-thinning ability of a tree, and it is used to determine the crown size. and predict the crown recession rate. This study simulated the HCB of Spruce fir broadleaved mixed forest in Northeast China using four non-parametric model approaches: generalized additive model, Cubist, boosted regression tree (BRT), and multiple adaptive regression spline. Because of the different genetic characteristics and growth patterns of different tree species, species-specific tree groups were formed, and the HCB of each species-specific group was simulated by the different models. Relative importance and partial dependence analyses were performed to identify the primary HCB predictors (including tree, stand, stand spatial structure, density and competition factors) and their relationships with the HCB of the four tree species groups. The relative importance was higher for individual tree variables (77.54 %, 31.02 %, 31.12 %, and 73.69 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively) and stand variables (5.00 %, 20.34 %, 11.03 %, and 8.71 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively) compared with stand spatial structure variables (4.57 %, 12.14 %, 21.91 %, and 5.89 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively), density indexes variables (2.17 %, 1.28 %, 4.05 %, and 2.87 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively), and tree species variables (10.79 %, 35.20 %, 31.90 %, and 8.84 % for coniferous, spruce-fir, hard broadleaved, and soft broadleaved groups, respectively). BRT and Cubist were the best approaches for modelling the four species-group specific HCBs. Although spatial structure variables had minor relative importance, further in-depth investigations are warranted.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102957"},"PeriodicalIF":5.8,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137563","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

Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-24 DOI: 10.1016/j.ecoinf.2024.102980

Nigela Tuerxun , Sulei Naibi , Jianghua Zheng , Renjun Wang , Lei Wang , Binbin Lu , Danlin Yu

Leaf chlorophyll content (LCC) is vital for photosynthesis and ecosystem functioning; it influences carbon, water, and energy exchanges while serving as an indicator of photosynthetic activity and nitrogen levels in precision agriculture. Hyperspectral data enable precise LCC monitoring by extracting spectral indices through optimal band combination (OBC) and predicting LCC with machine learning. However, OBC faces dimensionality issues, and machine learning models often overlook geographical influences, potentially reducing prediction accuracy. This study hypothesizes that developing spectral indices from important wavelengths and integrating geospatial data into machine learning models can address these issues and increase prediction accuracy. To test this hypothesis, a framework was developed that first uses elastic net (EN) and the successive projection algorithm (SPA) for wavelength selection, followed by spectral index creation with OBC and ranking with random forest (RF). Support vector regression (SVR), random forest regression (RFR), and geographically weighted least squares support vector regression (GWLS-SVR) were then used to assess the prediction accuracy. Finally, the optimal variables and regression model were identified. The results revealed that the EN- and SPA-based indices had stronger correlations and importance than defined indices. The double-difference index (DDn) and the anti-reflectance index (ARI) are the most robust three-dimensional and two-dimensional spectral indices, respectively. GWLS-SVR requires fewer indices (1–4) to achieve optimal results, with EN-DDn (2R₅₁₉-R₇₇₅-R₉₃₆)-GWLS-SVR performing best (R² = 0.95, RMSE = 0.61, PBIAS = -0.02). This research presents a robust framework with strong adaptability for estimating LCC in a specific study area and region, demonstrating substantial potential for the precise estimation of agroforestry vegetation parameters.

{"title":"Accurate estimation of Jujube leaf chlorophyll content using optimized spectral indices and machine learning methods integrating geospatial information","authors":"Nigela Tuerxun , Sulei Naibi , Jianghua Zheng , Renjun Wang , Lei Wang , Binbin Lu , Danlin Yu","doi":"10.1016/j.ecoinf.2024.102980","DOIUrl":"10.1016/j.ecoinf.2024.102980","url":null,"abstract":"<div><div>Leaf chlorophyll content (LCC) is vital for photosynthesis and ecosystem functioning; it influences carbon, water, and energy exchanges while serving as an indicator of photosynthetic activity and nitrogen levels in precision agriculture. Hyperspectral data enable precise LCC monitoring by extracting spectral indices through optimal band combination (OBC) and predicting LCC with machine learning. However, OBC faces dimensionality issues, and machine learning models often overlook geographical influences, potentially reducing prediction accuracy. This study hypothesizes that developing spectral indices from important wavelengths and integrating geospatial data into machine learning models can address these issues and increase prediction accuracy. To test this hypothesis, a framework was developed that first uses elastic net (EN) and the successive projection algorithm (SPA) for wavelength selection, followed by spectral index creation with OBC and ranking with random forest (RF). Support vector regression (SVR), random forest regression (RFR), and geographically weighted least squares support vector regression (GWLS-SVR) were then used to assess the prediction accuracy. Finally, the optimal variables and regression model were identified. The results revealed that the EN- and SPA-based indices had stronger correlations and importance than defined indices. The double-difference index (DDn) and the anti-reflectance index (ARI) are the most robust three-dimensional and two-dimensional spectral indices, respectively. GWLS-SVR requires fewer indices (1–4) to achieve optimal results, with EN-DDn (2<em>R</em><sub>519</sub>-<em>R</em><sub>775</sub>-<em>R</em><sub>936</sub>)-GWLS-SVR performing best (R<sup>2</sup> = 0.95, RMSE = 0.61, PBIAS = -0.02). This research presents a robust framework with strong adaptability for estimating LCC in a specific study area and region, demonstrating substantial potential for the precise estimation of agroforestry vegetation parameters.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102980"},"PeriodicalIF":5.8,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137581","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

A remote sensing-based strategy for mapping anthropogenic urban surface ecological poorness zones (AUSEPZ): A case study of Lisbon City

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-24 DOI: 10.1016/j.ecoinf.2024.102975

Mohammad Karimi Firozjaei , Naeim Mijani , Peter M. Atkinson

Anthropogenic activities play a crucial role in the formation and intensification of Urban Surface Ecological Poorness Zones (USEPZ). This study introduces a methodology for assessing the spatiotemporal fluctuations of Anthropogenic USEPZ (AUSEPZ), using Lisbon city and the Setúbal district as a case study to demonstrate its effectiveness. By integrating data from various surface characteristics through the Comprehensive Ecological Evaluation Index (CEEI), Surface Ecological Condition (SEC) maps were developed, and their spatial and temporal variations were analyzed. Additionally, a feature space was established between the Impervious Surface Percentage (ISP) and CEEI to calculate AUSEPZ intensity across different years. The findings revealed that the mean CEEI of Lisbon increased by 0.41 between 1986 and 2023. During this period, the proportions of SEC classified as Excellent, Very Good, Good, Fair, and Poor changed by −52 %, −13 %, +107 %, +444 %, and + 1134 %, respectively. The AUSEPZ intensity values for Lisbon were 0.32, 0.39, 0.46, 0.52, 0.57, and 0.63 for the years 1986, 1994, 2001, 2008, 2015, and 2023, respectively. The intensification of human activities, driven by urban expansion and population growth, has significantly contributed to the deterioration of SEC in Lisbon over recent years. These findings provide valuable insights for urban planners, policymakers, and stakeholders, enabling the design of targeted strategies to mitigate the impacts of urbanization and enhance ecological conditions in urban areas.

{"title":"A remote sensing-based strategy for mapping anthropogenic urban surface ecological poorness zones (AUSEPZ): A case study of Lisbon City","authors":"Mohammad Karimi Firozjaei , Naeim Mijani , Peter M. Atkinson","doi":"10.1016/j.ecoinf.2024.102975","DOIUrl":"10.1016/j.ecoinf.2024.102975","url":null,"abstract":"<div><div>Anthropogenic activities play a crucial role in the formation and intensification of Urban Surface Ecological Poorness Zones (USEPZ). This study introduces a methodology for assessing the spatiotemporal fluctuations of Anthropogenic USEPZ (AUSEPZ), using Lisbon city and the Setúbal district as a case study to demonstrate its effectiveness. By integrating data from various surface characteristics through the Comprehensive Ecological Evaluation Index (CEEI), Surface Ecological Condition (SEC) maps were developed, and their spatial and temporal variations were analyzed. Additionally, a feature space was established between the Impervious Surface Percentage (ISP) and CEEI to calculate AUSEPZ intensity across different years. The findings revealed that the mean CEEI of Lisbon increased by 0.41 between 1986 and 2023. During this period, the proportions of SEC classified as Excellent, Very Good, Good, Fair, and Poor changed by −52 %, −13 %, +107 %, +444 %, and + 1134 %, respectively. The AUSEPZ intensity values for Lisbon were 0.32, 0.39, 0.46, 0.52, 0.57, and 0.63 for the years 1986, 1994, 2001, 2008, 2015, and 2023, respectively. The intensification of human activities, driven by urban expansion and population growth, has significantly contributed to the deterioration of SEC in Lisbon over recent years. These findings provide valuable insights for urban planners, policymakers, and stakeholders, enabling the design of targeted strategies to mitigate the impacts of urbanization and enhance ecological conditions in urban areas.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102975"},"PeriodicalIF":5.8,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137561","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

A spatiotemporal optimization engine for prescribed burning in the Southeast US

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-23 DOI: 10.1016/j.ecoinf.2024.102956

Reetam Majumder , Adam J. Terando , J. Kevin Hiers , Jaime A. Collazo , Brian J. Reich

Many ecosystems in the Southeast US are dependent upon frequent low-intensity surface fires to sustain native biodiversity, ecosystem services, and endangered species populations. Today, landscape-scale prescribed fire is required to manage these systems for conservation objectives and to mitigate wildland fire risk. Successful application of prescribed fire in this region requires careful planning and assessment of the risks and tradeoffs involved when deciding whether or not to conduct a burn. Many of these risks are closely tied to ambient environmental conditions and are reflected in sets of ‘prescription’ parameters that define safe and effective operating conditions to meet objectives or regulatory requirements. To facilitate effective decision making and acknowledge growing uncertainties related to climate change effects on wildland fire operations, we developed a spatiotemporal optimization engine to identify near-term optimal burning opportunities for prescribed fire implementation. By mining historical 3-day numerical weather forecasts and observation-based weather data for 2015–2021, we have developed a Bayesian hierarchical model for forecast verification that provides calibrated daily weather forecasts and joint uncertainty estimates on meteorological variables of interest, with the latter serving as a measure of risk associated with prescribed fire activities. Burn allocation decisions are then optimized by considering this risk jointly with the utility of burning a particular habitat parcel. The initial iteration of the optimization engine is demonstrated through a case study of short-term meteorological conditions for the Eglin Air Force Base, located in Florida, USA. Results indicate agreement between the optimization engine and the observed past decision-making, with the largest divergences likely arising primarily from differences between utility functions presumed important and used to develop the optimization engine versus the true utility functions driving management behavior in practice.

{"title":"A spatiotemporal optimization engine for prescribed burning in the Southeast US","authors":"Reetam Majumder , Adam J. Terando , J. Kevin Hiers , Jaime A. Collazo , Brian J. Reich","doi":"10.1016/j.ecoinf.2024.102956","DOIUrl":"10.1016/j.ecoinf.2024.102956","url":null,"abstract":"<div><div>Many ecosystems in the Southeast US are dependent upon frequent low-intensity surface fires to sustain native biodiversity, ecosystem services, and endangered species populations. Today, landscape-scale prescribed fire is required to manage these systems for conservation objectives and to mitigate wildland fire risk. Successful application of prescribed fire in this region requires careful planning and assessment of the risks and tradeoffs involved when deciding whether or not to conduct a burn. Many of these risks are closely tied to ambient environmental conditions and are reflected in sets of ‘prescription’ parameters that define safe and effective operating conditions to meet objectives or regulatory requirements. To facilitate effective decision making and acknowledge growing uncertainties related to climate change effects on wildland fire operations, we developed a spatiotemporal optimization engine to identify near-term optimal burning opportunities for prescribed fire implementation. By mining historical 3-day numerical weather forecasts and observation-based weather data for 2015–2021, we have developed a Bayesian hierarchical model for forecast verification that provides calibrated daily weather forecasts and joint uncertainty estimates on meteorological variables of interest, with the latter serving as a measure of risk associated with prescribed fire activities. Burn allocation decisions are then optimized by considering this risk jointly with the utility of burning a particular habitat parcel. The initial iteration of the optimization engine is demonstrated through a case study of short-term meteorological conditions for the Eglin Air Force Base, located in Florida, USA. Results indicate agreement between the optimization engine and the observed past decision-making, with the largest divergences likely arising primarily from differences between utility functions presumed important and used to develop the optimization engine versus the true utility functions driving management behavior in practice.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102956"},"PeriodicalIF":5.8,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137528","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

net.raster: Interaction network metrics for raster data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-22 DOI: 10.1016/j.ecoinf.2024.102969

Cynthia Valéria Oliveira , Gabriela Alves-Ferreira , Flávio Mariano Machado Mota , Daniela Custódio Talora , Neander Marcel Heming

The interaction among species from different trophic levels is essential for ecosystem functioning and the use of bipartite networks is often useful for improving our understanding of multiple ecological processes, such as seed dispersal, pollination, and predation. Still, we are just paving ways to better understand spatial variation and macroecological aspects of interaction diversity. Here we introduce net.raster, an R package to calculate network and species-level metrics using rasterized presence-absence data and bipartite interaction networks as input, aiming to place species interaction studies into a spatial perspective. First, we focus on the spatialization of the functions and arguments from the bipartite R package using the terra package. Then, we enhance the visualisation of interaction patterns across space by allowing a raster layer of species interactions in addition to species distribution models (SDM). To date, all available packages that compute mutualistic network metrics rely only on matrices, or edge lists and network graphs derived from them. The net.raster package applies the calculations for each cell of a raster, allowing users to extrapolate known interactions across space and to visualise spatial patterns of bipartite network descriptors. The resulting rasters of interaction metrics are based mainly on the geographical extrapolation of interaction records between pairs of species and the resulting calculations use co-occurrence as a proxy for an interaction between species. Like other network analysis packages, net.raster allows users to calculate network topography indices using: a) the entire web, b) selecting the lower or upper level of each group, or c) selecting each species, choosing both levels or one level of interest at a time. Thus, the spatial processing and visualisation of fundamental bipartite networks provided by net.raster may fill a current gap in macroecological and biogeographical research and enable the understanding of the spatial variation of interaction networks. It also may open other questions in the macroecological and biogeographical study of networks, inspiring new insights into the conservation of important ecosystem services, such as seed dispersal and pollination.

{"title":"net.raster: Interaction network metrics for raster data","authors":"Cynthia Valéria Oliveira , Gabriela Alves-Ferreira , Flávio Mariano Machado Mota , Daniela Custódio Talora , Neander Marcel Heming","doi":"10.1016/j.ecoinf.2024.102969","DOIUrl":"10.1016/j.ecoinf.2024.102969","url":null,"abstract":"<div><div>The interaction among species from different trophic levels is essential for ecosystem functioning and the use of bipartite networks is often useful for improving our understanding of multiple ecological processes, such as seed dispersal, pollination, and predation. Still, we are just paving ways to better understand spatial variation and macroecological aspects of interaction diversity. Here we introduce <em>net.raster</em>, an R package to calculate network and species-level metrics using rasterized presence-absence data and bipartite interaction networks as input, aiming to place species interaction studies into a spatial perspective. First, we focus on the spatialization of the functions and arguments from the <em>bipartite</em> R package using the <em>terra</em> package. Then, we enhance the visualisation of interaction patterns across space by allowing a raster layer of species interactions in addition to species distribution models (SDM). To date, all available packages that compute mutualistic network metrics rely only on matrices, or edge lists and network graphs derived from them. The <em>net.raster</em> package applies the calculations for each cell of a raster, allowing users to extrapolate known interactions across space and to visualise spatial patterns of bipartite network descriptors. The resulting rasters of interaction metrics are based mainly on the geographical extrapolation of interaction records between pairs of species and the resulting calculations use co-occurrence as a proxy for an interaction between species. Like other network analysis packages, <em>net.raster</em> allows users to calculate network topography indices using: a) the entire web, b) selecting the lower or upper level of each group, or c) selecting each species, choosing both levels or one level of interest at a time. Thus, the spatial processing and visualisation of fundamental bipartite networks provided by <em>net.raster</em> may fill a current gap in macroecological and biogeographical research and enable the understanding of the spatial variation of interaction networks. It also may open other questions in the macroecological and biogeographical study of networks, inspiring new insights into the conservation of important ecosystem services, such as seed dispersal and pollination.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102969"},"PeriodicalIF":5.8,"publicationDate":"2024-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101991","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

dataFishing: An efficient Python tool and user-friendly web-form for mining mitochondrial and chloroplast sequences, taxonomic, and biodiversity data

IF 5.8 2区环境科学与生态学 Q1 ECOLOGY

Ecological Informatics

Pub Date : 2024-12-22 DOI: 10.1016/j.ecoinf.2024.102970

Luan Rabelo , Davidson Sodré , Oscar David Albito Balcázar , Murilo Furtado do Rosário , Aurycéia Jaquelyne Guimarães-Costa , Grazielle Gomes , Iracilda Sampaio , Marcelo Vallinoto

NCBI GenBank and BOLD Systems are important databases for biodiversity research, in which the deposited data can be used for various purposes, such as species identification analysis, evolutionary studies, biodiversity monitoring, as well as assessing the effects of possible climate changes on species distributions. Other information, such as taxonomy, collection site locations, and conservation status, is often critical for these studies. Some databases, such as GBIF, BOLD Systems, and GenBank, provide data on the taxonomy, habitat, and geographic distribution of various taxonomic groups, while others, such as WoRMS and IUCN, have specific data on marine species and conservation status. However, depending on the taxonomic group studied, searches in these databases can encompass dozens or hundreds of queries, forcing researchers to conduct extensive searches in each database, which is a time-consuming and error-prone process. To facilitate and automate access to this information, we introduce dataFishing, a Python script and a web form. dataFishing is faster and more efficient than other R packages, such as bold, taxize, rgbif, rredlist, and worrms, for obtaining taxonomic information from the consulted databases. Moreover, it allows the retrieval of DNA sequences, common names, synonyms, conservation status, and species occurrence points. This tool is free and will enable a more systematized and time-efficient search, which tends to facilitate such data inquiries.

{"title":"dataFishing: An efficient Python tool and user-friendly web-form for mining mitochondrial and chloroplast sequences, taxonomic, and biodiversity data","authors":"Luan Rabelo , Davidson Sodré , Oscar David Albito Balcázar , Murilo Furtado do Rosário , Aurycéia Jaquelyne Guimarães-Costa , Grazielle Gomes , Iracilda Sampaio , Marcelo Vallinoto","doi":"10.1016/j.ecoinf.2024.102970","DOIUrl":"10.1016/j.ecoinf.2024.102970","url":null,"abstract":"<div><div>NCBI GenBank and BOLD Systems are important databases for biodiversity research, in which the deposited data can be used for various purposes, such as species identification analysis, evolutionary studies, biodiversity monitoring, as well as assessing the effects of possible climate changes on species distributions. Other information, such as taxonomy, collection site locations, and conservation status, is often critical for these studies. Some databases, such as GBIF, BOLD Systems, and GenBank, provide data on the taxonomy, habitat, and geographic distribution of various taxonomic groups, while others, such as WoRMS and IUCN, have specific data on marine species and conservation status. However, depending on the taxonomic group studied, searches in these databases can encompass dozens or hundreds of queries, forcing researchers to conduct extensive searches in each database, which is a time-consuming and error-prone process. To facilitate and automate access to this information, we introduce dataFishing, a Python script and a web form. dataFishing is faster and more efficient than other R packages, such as <em>bold</em>, <em>taxize</em>, <em>rgbif</em>, <em>rredlist</em>, and <em>worrms</em>, for obtaining taxonomic information from the consulted databases. Moreover, it allows the retrieval of DNA sequences, common names, synonyms, conservation status, and species occurrence points. This tool is free and will enable a more systematized and time-efficient search, which tends to facilitate such data inquiries.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102970"},"PeriodicalIF":5.8,"publicationDate":"2024-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137562","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