Ecological Informatics最新文献

{"title":"Aboveground biomass inversion of forestland in a Jinsha River dry-hot valley by integrating high and medium spatial resolution optical images: A case study on Yuanmou County of Southwest China","authors":"Zihao Liu ,&nbsp;Tianbao Huang ,&nbsp;Yong Wu ,&nbsp;Xiaoli Zhang ,&nbsp;Chunxiao Liu ,&nbsp;Zhibo Yu ,&nbsp;Can Xu ,&nbsp;Guanglong Ou","doi":"10.1016/j.ecoinf.2024.102796","DOIUrl":"10.1016/j.ecoinf.2024.102796","url":null,"abstract":"<div><p>It is crucial to develop a comprehensive method for estimating the aboveground biomass (AGB) of trees, shrubs, grasslands, and sparse tree areas in ecologically fragile dry, hot valley regions with vertical zonation. Multi-source remote-sensing data can fulfill this requirement, providing help in monitoring the health of ecosystems and providing a basis for regional biodiversity conservation and restoration. Sentinel-2A satellite imagery was used to classify the forests, shrubs, and grasslands in Yuanmou County, Chuxiong Yi Autonomous Prefecture, Yunnan Province, China. The Gaofen-2 satellite (GF-2) was used to extract the canopy width and calculate tree biomass in the valley-type savanna region. These data were combined with remote-sensing factors and measured survey data, and random forest (RF) and extreme gradient boosting (XGBoost) models were used to estimate the biomass. Using GF-2 images to segment sparse tree areas effectively reduced the overestimation of low-resolution remote-sensing images, enabling the AGB of sparse trees to be accurately estimated. The biomass estimations based on the Sentinel-2A images attained coefficient of determination (<em>R</em>²) values of 0.45 and 0.47 for the forest, 0.55 and 0.61 for the shrubs, and 0.32 and 0.37 for the grasslands using RF and XGBoost models, respectively, demonstrating variable effectiveness across vegetation types. In addition, the XGBoost model was more robust than the RF model for all three vegetation types. Our methodology provides scientific support for the sustainable development of ecologically fragile dry, hot valleys and savanna areas.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003388/pdfft?md5=f506a70c66cbd6e3955a7dc2b7fe8e55&pid=1-s2.0-S1574954124003388-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098110","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}

{"title":"The impact of land-use change on the ecological environment quality from the perspective of production-living-ecological space: A case study of the northern slope of Tianshan Mountains","authors":"Yu Cao ,&nbsp;Mingyu Zhang ,&nbsp;Zhengyong Zhang ,&nbsp;Lin Liu ,&nbsp;Yu Gao ,&nbsp;Xueying Zhang ,&nbsp;Hongjin Chen ,&nbsp;Ziwei Kang ,&nbsp;Xinyi Liu ,&nbsp;Yu Zhang","doi":"10.1016/j.ecoinf.2024.102795","DOIUrl":"10.1016/j.ecoinf.2024.102795","url":null,"abstract":"<div><p>Elucidating the relationships between production-living-ecological space (PLES) and ecological environments can help identify new strategies to promote sustainable development. The northern slope of the Tianshan Mountains represents a typical complex ecosystem characterized by mountain-oasis-desert interactions in arid regions with prominent human-land conflicts and intricate ecological environments. Here, we analyzed the spatiotemporal variations in land use in the study area from the perspective of PLES. Based on moderate resolution imaging spectroradiometer (MODIS) data, an improved remote sensing ecological index (IRSEI) suitable for arid areas was established to evaluate the eco-environment quality (EEQ) by introducing salinity and cleanliness indexes. A stepwise regression model was then used to identify and quantify the impact of the PLES transfer modes on EEQ. The results showed that: (1) The oasis area was dominated by agricultural production land, whereas the desert and alpine areas were dominated by other and pasture ecological lands, respectively. The oasis area primarily involved the conversion of pasture ecological land to agricultural production land, whereas the desert and alpine areas showed mutual transformation of ecological space. (2) The size relationship of the EEQ in each sub-region was alpine region (0.555) &gt; oasis region (0.509) &gt; desert region (0.424). The EEQ in the study area showed an overall upward trend but decreased in the alpine region. (3) Changes in the PLES and IRSEI primarily occurred in the oasis region. Among the 21 PLES transfer modes that affect EEQ, an increase in agricultural production land was the primary mode that enhanced IRSEI, whereas an increase in impervious surfaces significantly decreased IRSEI. The degree of influence was as follows: industrial and mining production (−0.594) &gt; urban living (−0.462) &gt; rural living land (−0.316). In addition, EEQ is also affected by the combined effects of climate, topography, and other factors. By proposing IRSEI, we highlight the impact of land-use transfer mode on ecological environment quality from the perspective of PLES, which can provide a reference for ecological environment evaluation in arid areas and is of great significance for land-use planning and ecological environment protection.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003376/pdfft?md5=cf36b8be4c19dbed11c0acd1bf9d669a&pid=1-s2.0-S1574954124003376-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086853","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}

{"title":"A hyperspectral metal concentration inversion method using attention mechanism and graph neural network","authors":"Lei Zhang","doi":"10.1016/j.ecoinf.2024.102792","DOIUrl":"10.1016/j.ecoinf.2024.102792","url":null,"abstract":"<div><p>Soil heavy metal contamination has emerged as a global environmental concern, posing significant risks to human health and ecosystem integrity. Hyperspectral technology, with its non-invasive, non-destructive, large-scale, and high spectral resolution capabilities, shows promising applications in monitoring soil heavy metal pollution. Traditional monitoring methods are often time-consuming, labor-intensive, and expensive, limiting their effectiveness for rapid, large-scale assessments. This study introduces a novel deep learning method, SpecMet, for estimating heavy metal concentrations in naturally contaminated agricultural soils using hyperspectral data. The SpecMet model extracts features from hyperspectral data using convolutional neural networks (CNNs) and achieves end-to-end prediction of soil heavy metal concentrations by integrating attention mechanisms and graph neural networks. Results demonstrate that the OR-SpecMet model, which utilizes raw spectral data, achieves optimal prediction performance, significantly surpassing traditional machine learning methods such as multiple linear regression, partial least squares regression, and support vector machine regression in estimating concentrations of lead (Pb), copper (Cu), cadmium (Cd), and mercury (Hg). Moreover, training specialized OR-SpecMet models for individual heavy metals better accommodates their unique spectral-concentration relationships, enhancing overall estimation accuracy while achieving a 20.3 % improvement in predicting low-concentration mercury. The OR-SpecMet method showcases the superior performance and extensive application potential of deep learning techniques in precise soil heavy metal pollution monitoring, offering new insights and reliable technical support for soil pollution prevention and agricultural ecosystem protection. The code and datasets used in this study are publicly available at: <span><span>https://github.com/zhang2lei/metal.git</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003340/pdfft?md5=408d86a5a8c2f813bf658873fbbc0a9d&pid=1-s2.0-S1574954124003340-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098107","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}

{"title":"Lightweight and accurate aphid detection model based on an improved deep-learning network","authors":"Weihai Sun ,&nbsp;Yane Li ,&nbsp;Hailin Feng ,&nbsp;Xiang Weng ,&nbsp;Yaoping Ruan ,&nbsp;Kai Fang ,&nbsp;Leijun Huang","doi":"10.1016/j.ecoinf.2024.102794","DOIUrl":"10.1016/j.ecoinf.2024.102794","url":null,"abstract":"<div><p>Rapid and accurate detection of bamboo aphids can help prevent large-scale aphid infestations from occurring, which is of great significance for increasing bamboo shoot production and economic benefits. Herein, a lightweight and accurate model, SCA-YOLOv5s, was established by integrating ShuffleNetv2 and Coordinate Attention with the YOLOv5s model to detect <em>Takecallis taiwanus</em> on the yellow sticky traps. Specifically, we first replaced the backbone network of YOLOv5s with ShuffleNetv2 to reduce the number of parameters and computational complexity of the model. Second, an anchor optimization method was proposed by combining linear scaling and <em>k</em>-means algorithm to generate appropriate anchor boxes for detecting small-sized alate aphids. Third, the coordinate attention mechanism was added to the neck network to improve the feature extraction ability. To verify the performance of the proposed SCA-YOLOv5s model, eight detection models were constructed with existing deep learning methods, including SSD300, YOLOv3, Faster R-CNN, YOLOv4, YOLOv4-Tiny, YOLOX-Tiny, YOLOv7-Tiny, and YOLOv5s. Results reveal that the SCA-YOLOv5s model achieved higher detection accuracy than the other eight models. Its mean average precision reached 92.2 %. The proposed model has a size of only 6.7 MB, its floating-point operations (FLOPs) is 7.4 × 10⁹, its inference time is 6.6 ms, and compared with YOLOv5s, it is 53.47 % smaller in model size, 55.15 % lower in FLOPs, and 0.8 ms faster in inference time. The results indicate that the proposed model can maintain high detection accuracy while minimizing computation and inference time, which is crucial for deployment in remote areas with low information technology. This study provides valuable technical support for the control of aphids in bamboo forests.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003364/pdfft?md5=7405cde5930c97d6d4719ddf73d64b30&pid=1-s2.0-S1574954124003364-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098108","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}

{"title":"Attributing spatially stratified heterogeneity in biodiversity of urban–rural interlaced zones based on the OPGD model","authors":"Di Wang ,&nbsp;Lang Zhang ,&nbsp;Haoran Yu ,&nbsp;Qicheng Zhong ,&nbsp;Guilian Zhang ,&nbsp;Xuanying Chen ,&nbsp;Qingping Zhang","doi":"10.1016/j.ecoinf.2024.102789","DOIUrl":"10.1016/j.ecoinf.2024.102789","url":null,"abstract":"<div><p>Urban–rural interlaced zones are characterized by the interpenetration of urban and rural elements, drastic changes in construction, relatively weak planning and management, and anthropogenic activities that constantly impact the ecological background. However, the ecological barriers and hinterland spaces of the city center provide important ecological functions. In this study, we selected forest birds as indicator species of the urban ecological environment and explored the spatial stratification and heterogeneity effects of environmental substrates and anthropogenic activities on bird diversity (species richness, abundance, Shannon–Wiener index, and Simpson index) in urban–rural interlaced zones using the optimal parameter geographic detector model to characterize the changes in ecological functions in these zones. The results of this study are as follows:</p><p>(1) The bird diversity index in Minhang District, Shanghai, showed an obvious urban-rural gradient divergence with the transition of urban zone- rural-urban interface - rural zone.</p><p>An agglomerative spatial differentiation pattern was observed more in the southeast but less in the northwest, with a high degree of spatial distribution concentrations and evident imbalance characteristics.</p><p>(2) The spatially stratified heterogeneity in bird diversity in urban–rural interlaced zones was because of the combined action of multiple driving factors under the three dimensions of habitat environment, degree of urbanization, and anthropogenic interference. Most of the interactions between any two factors showed non-linear or bifactorial enhancement effects. Furthermore, the one-factor explanatory power of urbanization and anthropogenic interference factors on bird diversity was significantly higher than that of the habitat environment factor.</p><p>(3) Population heat distribution (PD), distance to the center of Shanghai (DC), and nighttime lighting index(NTL) were the main drivers of spatially stratified heterogeneity in bird diversity and the key indicators of urban–rural gradient changes. The interaction between PD and DC had the strongest explanatory power for the spatial differentiation of bird diversity.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003315/pdfft?md5=aa2a3267933efe8c74a138e4c8987bd5&pid=1-s2.0-S1574954124003315-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142173881","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}

{"title":"YOLO-SAG: An improved wildlife object detection algorithm based on YOLOv8n","authors":"Lingli Chen ,&nbsp;Gang Li ,&nbsp;Shunkai Zhang ,&nbsp;Wenjie Mao ,&nbsp;Mei Zhang","doi":"10.1016/j.ecoinf.2024.102791","DOIUrl":"10.1016/j.ecoinf.2024.102791","url":null,"abstract":"<div><p>Wildlife conservation is crucial for maintaining biodiversity, ensuring ecosystem balance and stability, and fostering sustainable development. Currently, the use of infrared camera traps to monitor and capture photos of wildlife is a vital methodology in protecting and researching wildlife, and automatic detection and identification of animals within captured photographs are paramount. However, factors such as the complexity of the field environment and the varying sizes of animal targets lead to low detection accuracy, while high-precision detection models are hindered by high computational complexity and sluggish training speeds. This paper proposes a wildlife target detection algorithm based on improved YOLOv8n - YOLO-SAG, which aims to balance accuracy and speed. Training stability is enhanced by introducing the Softplus activation function, which increases detection accuracy; incorporating the AIFI enhances intra-scale feature interaction, reducing missed and false detections. Integrating the GSConv and VoV-GSCSP module lightens neck convolutions, reducing computational redundancy and balancing the computational and parametric quantities brought by the AIFI. Experimental results on a self-made wildlife dataset indicate that the YOLO-SAG achieves 94.9%, 90.9%, 96.8%, and 79.9% in Precision, Recall, [email protected], and [email protected]–0.95, respectively, which are 3.4%, 3.3%, 3.2%, and 4.9% higher than the original YOLOv8n. Inference and post-processing times reach 1.2 ms and 0.5 ms, a speedup of 25% and 54.5%, respectively, and the computation volume is only 7.2 GFLOPs, an 11.1% decrease.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003339/pdfft?md5=fabe82c2fff9fc5f7d0c7fd3b9cca85a&pid=1-s2.0-S1574954124003339-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086858","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}

{"title":"Evaluation of driving effects of carbon storage change in the source of the Yellow River: A perspective with CMIP6 future development scenarios","authors":"Ming Ling ,&nbsp;Zihao Feng ,&nbsp;Zizhen Chen ,&nbsp;Yanping Lan ,&nbsp;Xinhong Li ,&nbsp;Haotian You ,&nbsp;Xiaowen Han ,&nbsp;Jianjun Chen","doi":"10.1016/j.ecoinf.2024.102790","DOIUrl":"10.1016/j.ecoinf.2024.102790","url":null,"abstract":"<div><p>Understanding how future climate scenarios impact land use/cover (LUC) and carbon storage (CS) is crucial for achieving carbon neutrality. However, research often overlooks the spatiotemporal impacts of future climate and socioeconomic changes on CS. This study integrates system dynamic (SD), patch-generating land use simulation (PLUS), the integrated valuation of ecosystem services and tradeoffs (InVEST) model, and the geographical detector to assess the LUC and CS evolution in the source of the Yellow River (SYR) from 2020 to 2060. Utilizing carbon density and LUC data, we explored the influence of natural and socioeconomic factors on CS under five shared socioeconomic pathways and representative concentration pathways (SSP-RCPs) scenarios. Our findings demonstrate that: (1) Ecological land, including woodland, grassland, and wetland, expanded more under SSP126 compared to SSP245, with SSP345, SSP460, and SSP585 showing a trend of degradation tied to deeper economic contribution. (2) By 2060, CS in terrestrial ecosystem under SSP126, SSP245, SSP345, SSP460, and SSP585 were 702.33 × 10⁶ t, 700.33 × 10⁶ t, 697.22 × 10⁶ t, 696.03 × 10⁶ t, and 691.21 × 10⁶ t, respectively. This represents changes of 3.69 × 10⁶ t, 1.69 × 10⁶ t, −1.49 × 10⁶ t, −2.68 × 10⁶ t, and −7.43 × 10⁶ t compared to 2020. (3) Soil type predominantly influenced the spatial differentiation of CS, with significant interactions with precipitation. This research provides new insights into land redistribution, economic strategies, and achieving carbon neutrality.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003327/pdfft?md5=3f165f4f1af317e0955cb37488225858&pid=1-s2.0-S1574954124003327-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142076996","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}

{"title":"Analysing the capacity of multispectral indices to map the spatial distribution of potential post-fire soil losses based on soil burn severity","authors":"Ana Novo ,&nbsp;Cristina Fernández ,&nbsp;Clara Míguez ,&nbsp;Estefanía Suárez-Vidal","doi":"10.1016/j.ecoinf.2024.102793","DOIUrl":"10.1016/j.ecoinf.2024.102793","url":null,"abstract":"<div><p>The area burned in Spain exceeded historical records in 2022, when exceptionally warm conditions influenced wildfire events. The predicted intensification of wildfire regimes includes an increase in frequency, severity, and size. Therefore, a study of the wildfires that occurred in 2022 is necessary to understand their behaviour and possible environmental impacts. The objective of this study is to analyse the applicability of using spectral indices and Geographic Information System (GIS) approaches to map the spatial distribution and estimate potential soil losses using Sentinel-2 imagery and fire severity field data. Soil losses were estimated using an empirical model based on soil burn severity data collected in the field after wildfire. The relationship between the Normalized Difference Infrared Index (NDII), Difference Normalized Wildfire Ash Index (dNWAI), and the Blue Normalized Difference Vegetation Index (BNDVI) with the estimated soil losses was then evaluated. In addition, the influence of different time scales of the satellite images was analysed. The first period considered (Date I) ranges from 8 to 20 days after the beginning of the wildfire, which coincides with the field data collection. The second period considered (Date II) ranges from 28 to 35 days after the start of the wildfire. The results obtained showed a significant dependence relationship between the BNDVI index (using satellite images of Date I) and the estimated soil losses (R² = 0.756), while the results of the NDII (R² = 0.31) and dNWAI (R² = 0.061), showed no spatial relationship with the estimated soil losses. Three of the largest wildfires in 2022 in Spain were analysed, and the results showed strong correlations of BNDVI index for Folgoso do Courel (R² = 0.808), for Carballeda de Valedorras (R² = 0.906), and for Sierra de la Culebra (R² = 0.939). In addition, these results allowed the mapping and quantification of potential soil losses in areas where fire severity was high, totalling ∼2,50,000 Mg ha⁻¹ in Folgoso do Courel, ∼3,70,000 Mg ha⁻¹ in Carballeda de Valdeorras, and ∼4,70,000 Mg ha⁻¹ in Sierra de la Culebra. Moreover, BNDVI values for estimating soil loss vary by vegetation type, and there is a positive correlation between severity classes and the BNDVI index. This approach can inform post-fire land management decisions in future wildfires and could be applied to other regions.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003352/pdfft?md5=64382a314c6fdc9b93458e6684c44ece&pid=1-s2.0-S1574954124003352-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142077311","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}

{"title":"An app for tree trunk diameter estimation from coarse optical depth maps","authors":"Zhengpeng Feng, Mingyue Xie, Amelia Holcomb, Srinivasan Keshav","doi":"10.1016/j.ecoinf.2024.102774","DOIUrl":"https://doi.org/10.1016/j.ecoinf.2024.102774","url":null,"abstract":"Trunk diameter is related to the overall health and level of carbon sequestration in a tree. Trunk diameter measurement, therefore, is a key task in both forest plot and urban settings. Unlike the traditional approach of manual measurement with a measuring tape or calipers, several recent approaches rely on sophisticated technologies such as LiDAR and time-of-flight cameras that provide fine-grain depth maps, which are used for depth-assisted image segmentation in downstream processing. These technologies are supported only on specialized devices or high-end smartphones. We present a mobile application that uses coarse-grain depth maps derived from an optical sensor, and so can be run on most common Android devices. Moreover, we use a state-of-the-art deep neural network to estimate trunk diameter from an image and its corresponding coarse depth map (RGB-D). We tested our app using a data set collected from four countries and under challenging conditions including occlusion, leaning trees, and irregular shapes and found that our algorithm has a MAE of 1.66 cm and an RMSE of 2.46 cm, which is comparable to accuracy from fine-grain depth maps. Moreover, diameter measurement using our app is >5 times faster than traditional manual surveying.","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.1,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimisation of the adaptive neuro-fuzzy inference system for adjusting low-cost sensors PM concentrations","authors":"Martina Casari ,&nbsp;Piotr A. Kowalski ,&nbsp;Laura Po","doi":"10.1016/j.ecoinf.2024.102781","DOIUrl":"10.1016/j.ecoinf.2024.102781","url":null,"abstract":"<div><p>Driven by the urgent necessity for accurate environmental data in urban settings, this research leverages the Adaptive Neuro-Fuzzy Inference System (ANFIS) as a machine learning-based approach to refine SPS30 low-cost sensor data influenced by hygroscopicity in Turin, Italy. Employing ANFIS offers several advantages: it enhances clarity regarding the correspondence between output and input values and rules, improves system interpretability, and facilitates the representation of linguistic variables and rules, thereby encouraging domain experts' involvement in enhancing the system's performance as needed. This paper illustrates the utility of ANFIS in adjusting the detected particulate matter (PM) concentration and compares its effectiveness with other established machine-learning techniques, including linear regression, decision trees, random forest, SVR and a multilayer perceptron (MLP). These methods are chosen as benchmarks owing to their established effectiveness in calibration procedures.</p><p>We propose certain preprocessing steps for detecting and rectifying anomalies, alongside introducing two distinct data-splitting methodologies. Additionally, a discussion about feature selection is presented to elucidate the impact of specific features on performance enhancement. The efficacy of ANFIS in refining PM data is demonstrated through a comparative assessment, where it outperforms all the established machine-learning techniques. Notably, incorporating only PM2.5, relative humidity and temperature as features yields optimal performance while mitigating overfitting issues. The paper also explores various ANFIS configurations, including two distinct optimization algorithms, and investigates the impact of the number and type of membership functions on the fuzzy system's performance. Our study highlights the potential of the Adaptive Neuro-Fuzzy Inference System as a versatile and effective tool for addressing real-world challenges in environmental sensing.</p></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1574954124003236/pdfft?md5=8c5746f81497cb3a2e1b0d3f2cb3ae48&pid=1-s2.0-S1574954124003236-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142098106","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}