Article
Environmental Sciences
Seok Min Hong, Sang-Soo Baek, Daeun Yun, Yong-Hwan Kwon, Hongtao Duan, JongCheol Pyo, Kyung Hwa Cho
Summary: This study applied a deep neural network model to monitor the vertical distribution of harmful algal pigments in inland waters, using drone-borne hyperspectral imagery. The ResNet-18 model showed the best performance with an R-2 value of 0.70, and Gradient-weighted Class Activation Mapping (Grad-CAM) highlighted informative reflectance band ranges for pigment estimation. This research demonstrated the potential of explainable deep learning models with hyperspectral images to estimate Chl-a, PC, and Turb vertical distributions and reveal influential features for describing vertical profile phenomena.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Remote Sensing
Kirrilly Pfitzner, Renee Bartolo, Timothy Whiteside, David Loewensteiner, Andrew Esparon
Summary: The relationship between species phenology and spectral separability is important for determining the optimal remote sensing sampling period to maximize spectral separability of vegetation species. In this study, the researchers measured the in-situ hyperspectral response of various understorey species in tropical savannas and found that most species displayed a photosynthetic spectral response with increased greenness at the end of the wet season, gradually declining as vegetation dried out. These findings have implications for determining the ideal sampling period for measuring outdoor canopy reflectance of understorey species.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Environmental Sciences
Ryan E. O'Shea, Nima Pahlevan, Brandon Smith, Mariano Bresciani, Todd Egerton, Claudia Giardino, Lin Li, Tim Moore, Antonio Ruiz-Verdu, Steve Ruberg, Stefan G. H. Simis, Richard Stumpf, Diana Vaiciute
Summary: The study developed a machine-learning model, MDNs, trained on a large dataset, to estimate phycocyanin concentration from hyperspectral satellite remote sensing measurements. The model demonstrated superior performance on HICO and PRISMA datasets compared to multispectral algorithms, particularly in accurately estimating low PC values.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Paolo Tasseron, Tim van Emmerik, Joseph Peller, Louise Schreyers, Lauren Biermann
Summary: This study analyzed a high-resolution hyperspectral image database of plastic debris and vegetation, determining 12 satellite bands for discrimination between these classes. In addition, NDVI and FDI were calculated to understand their effectiveness and potential improvements.
Article
Environmental Sciences
Juha Suomalainen, Raquel A. Oliveira, Teemu Hakala, Niko Koivumaki, Lauri Markelin, Roope Nasi, Eija Honkavaara
Summary: This study introduces the application of drones in environmental monitoring and the development of a workflow for direct reflectance transformation, with improved accuracy of reflectance factors through effective radiometric calibration and atmospheric correction methods. Experimental tests demonstrate high accuracy of the workflow, suitable for tasks such as forest monitoring, large-scale autonomous mapping, and real-time applications.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Marion Jaud, Guillaume Sicot, Guillaume Brunier, Emma Michaud, Nicolas Le Dantec, Jerome Ammann, Philippe Grandjean, Patrick Launeau, Gerard Thouzeau, Jules Fleury, Christophe Delacourt
Summary: Hyper-DRELIO is a custom mini-UAV platform equipped with a hyperspectral sensor for environmental observations, and in this study, in situ radiometric corrections were developed for the sensor using simple equipment such as Spectralon and a field spectrometer. The efficiency of the corrections was evaluated by comparing spectra from the imagery to in situ measurements, showing good consistency and potential for quantifying and mapping intertidal ecosystems.
Article
Optics
Stefan G. H. Simis, Peter D. Hunter, Mark W. Matthews, Evangelos Spyrakos, Andrew Tyler, Diana Vaiciute
Summary: Estimating water constituent concentration using hyperspectral reflectance relies on a method that retrieves the backscattering coefficient from selected wavebands and improves the estimation of chlorophyll-a.
Article
Environmental Sciences
Wonjin Jang, Yongeun Park, JongCheol Pyo, Sanghyun Park, Jinuk Kim, Jin Hwi Kim, Kyung Hwa Cho, Jae-Ki Shin, Seongjoon Kim
Summary: Understanding the concentration and distribution of cyanobacteria blooms is crucial for managing water quality and protecting aquatic ecosystems. This study applies airborne hyperspectral imagery and data-driven algorithms to effectively estimate the main pigments of cyanobacteria and evaluate their spatio-temporal distribution. The proposed algorithm shows promising results in detecting cyanobacteria occurrence and can contribute to suitable water quality management plans.
Article
Remote Sensing
Lei Deng, Yong Chen, Yun Zhao, Lin Zhu, Hui-Li Gong, Li-Jie Guo, Han-Yue Zou
Summary: This study utilized UAV-based oblique photography technology to obtain high-spatial resolution and high-accuracy continuous RA data, optimizing the selection of multi-angle observation data using the Monte Carlo method. The accuracy and applicability of two BRDF inversion models were thoroughly analyzed and compared, expanding the research and application of RA measurement.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Chemistry, Analytical
Mariana A. Soppa, Brenner Silva, Francois Steinmetz, Darryl Keith, Daniel Scheffler, Niklas Bohn, Astrid Bracher
Summary: This study investigates the performance of Polymer AC for hyperspectral remote sensing over coastal waters, demonstrating its potential in providing lower uncertainties and greater data coverage compared to the standard AC algorithm. Polymer shows very good performance in the green spectral region and higher spectral similarity to in situ measurements.
Article
Astronomy & Astrophysics
Paolo F. Tasseron, Louise Schreyers, Joseph Peller, Lauren Biermann, Tim van Emmerik
Summary: Plastic pollution in aquatic ecosystems has increased significantly, impacting both humans and aquatic life. Innovative approaches are needed to monitor the presence, abundance, and types of plastic in these ecosystems. The use of multi- and hyperspectral cameras is gaining popularity, but most experiments have been conducted in controlled environments, limiting their applicability to natural environments. This study presents a method that links lab- and field-based identification of macroplastics using hyperspectral data, providing insights into plastic detection in natural settings.
EARTH AND SPACE SCIENCE
(2022)
Article
Agronomy
Nik Norasma Che'Ya, Ernest Dunwoody, Madan Gupta
Summary: The study successfully discriminated weed species in sorghum fields using hyperspectral data, which were later detected and analyzed using multispectral images. The results showed that the differences between weed species and sorghum could be successfully detected through this method, with the highest spatial resolution yielding the highest accuracy for weed detection.
Article
Engineering, Electrical & Electronic
Erika Piaser, Andrea Berton, Rossano Bolpagni, Michele Caccia, Maria Beatrice Castellani, Andrea Coppi, Alice Dalla Vecchia, Francesca Gallivanone, Giovanna Sona, Paolo Villa
Summary: Advancements in airborne imaging spectroscopy have enabled the use of lightweight drones for detailed vegetation assessment. However, surface reflectance anisotropy and view-illumination effects may bias the extracted spectra and derived spectral indices, particularly in aquatic vegetation. This study empirically investigated the impact of illumination conditions and angular configurations on radiometric variability of centimetric resolution drone data over different aquatic plant species. The findings showed a decrement in reflectance under diffuse light conditions and a marked angular reflectance anisotropy in high absorption spectral regions for aquatic vegetation.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Agronomy
Shuai Che, Guoying Du, Xuefeng Zhong, Zhaolan Mo, Zhendong Wang, Yunxiang Mao
Summary: A high-throughput, nondestructive, optical method based on hyperspectral imaging technology was developed for phenotyping the pigments in Neopyropia. The best prediction models were established using preprocessing methods and machine learning techniques. This method enables fast, accurate, and noninvasive evaluation of pigment content and distribution in Neopyropia, with important implications for macroalgae breeding and phenomics research.
Article
Engineering, Environmental
Yuan Cao, Yue Li, Ling Ren, Mengqiao Sha, Dongqing Lv, Sen Wang, Fanlong Kong
Summary: This study successfully mitigated bio-clogging in constructed wetlands using rhamnolipids and citric acid as solubilizers, improving the removal efficiency of NH4+-N and COD.
CHEMICAL ENGINEERING JOURNAL
(2021)
Article
Engineering, Environmental
Dong Liu, Zhandong Sun, Ming Shen, Liqiao Tian, Shujie Yu, Xintong Jiang, Hongtao Duan
Summary: A new method has been developed to remotely observe the three-dimensional distribution of particulate organic carbon (POC) storage in shallow eutrophic lakes using satellite data. This study is significant for understanding the carbon cycle in such lakes.
Article
Environmental Sciences
Yuanshan Liao, Haijin Lan, Xinyue Zhang, Zhenjing Liu, Mi Zhang, Zhenghua Hu, Hongtao Duan, Qitao Xiao
Summary: Lakes are important sources of atmospheric methane, and the emissions from the river inlet region are less studied. Field measurements at Lake Taihu over six years show that the river inlet region is a hot spot of CH4 emission, with a seven times higher annual mean value compared to the pelagic region. The variability of CH4 emission is linked to pollution loadings and CH4-rich water in the inflowing river.
Article
Environmental Sciences
Xintong Jiang, Dong Liu, Junli Li, Hongtao Duan
Summary: Dissolved organic matter (DOM) plays a vital role in the global lake carbon cycle. This study focused on the changes in DOM components in different lake types based on in situ data from ten lakes in northwestern China. The results showed that human activities and salinity were the main contributors to the variations in DOM concentration and composition in the western arid lakes. The study also proposed a feasible flowchart for remotely estimating DOM in saline lakes using satellite data.
ENVIRONMENTAL RESEARCH
(2023)
Article
Environmental Sciences
Juhua Luo, Guigao Ni, Yunlin Zhang, Kang Wang, Ming Shen, Zhigang Cao, Tianci Qi, Qitao Xiao, Yinguo Qiu, Yongjiu Cai, Hongtao Duan
Summary: This study presents a novel three-step classification algorithm based on Landsat imagery for the identification and monitoring of lake vegetation and algal bloom. The algorithm was validated on 22 lakes in the middle and lower reaches of the Yangtze River and applied to Landsat data from 1985 to 2021. The results show a significant decrease in lake vegetation and an increase in algal bloom in the study area, indicating an ongoing transition from a macrophyte-dominated state to a phytoplankton-dominated state.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Yinguo Qiu, Yaqin Jiao, Juhua Luo, Zhenyu Tan, Linsheng Huang, Jinling Zhao, Qitao Xiao, Hongtao Duan
Summary: This paper proposes a novel rapid reconstruction scheme for water regions in 3D models of oblique photography, which can achieve fast and accurate reconstruction. Experimental results show that this scheme can improve the current UAV oblique photography 3D modeling technique and expand its application in twin watershed, twin city, and other areas.
Article
Engineering, Environmental
Hongtao Duan, Qitao Xiao, Tianci Qi, Cheng Hu, Mi Zhang, Ming Shen, Zhenghua Hu, Wei Wang, Wei Xiao, Yinguo Qiu, Juhua Luo, Xuhui Lee
Summary: This study compares eight machine learning models to predict methane emissions from lakes using satellite remote sensing. The random forest model achieves the best accuracy. The study also finds that climate warming and algal blooms contribute to the long-term increase in methane emissions.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2023)
Article
Environmental Sciences
Zhigang Cao, Chuanmin Hu, Ronghua Ma, Hongtao Duan, Miao Liu, Steven Loiselle, Kaishan Song, Ming Shen, Dong Liu, Kun Xue
Summary: This study developed a machine learning model to generate SPM time series in 269 lakes across China from 2002 to 2021. The study found that SPM concentrations showed a significant decrease in the 21st century, with different changing patterns in different climate zones and ecoregions.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Jinge Ma, Steven Loiselle, Zhigang Cao, Tianci Qi, Ming Shen, Juhua Luo, Kaishan Song, Hongtao Duan
Summary: Under the influence of climate warming and human activities, large lakes worldwide have experienced an increase in eutrophication and algal blooms. This study utilizes daily satellite observations to develop an algorithm that accurately identifies the spatiotemporal distribution of algal bloom dynamics in large lakes. The findings show positive trends in bloom area, frequency, and an earlier bloom time, with climate factors and human activities identified as key drivers.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Engineering, Environmental
Ming Shen, Zhigang Cao, Liqiang Xie, Yanyan Zhao, Tianci Qi, Kaishan Song, Lili Lyu, Dian Wang, Jinge Ma, Hongtao Duan
Summary: Cyanobacterial blooms and the release of algal toxins pose a serious threat to the safety of drinking water sources. However, the monitoring and evaluation of algal toxins in lake water have not been carried out regularly. This study developed a remote sensing scheme based on satellite data to assess the risk of algal toxins and found that most large lakes in eastern China had experienced high risk at least once. Fortunately, the frequency of high human health risks in terms of lake areas was low, indicating the potential to set drinking water intakes in most waters while reducing cyanobacterial blooms.
Article
Remote Sensing
Zhenyu Tan, Chen Yang, Yinguo Qiu, Wei Jia, Chenxi Gao, Hongtao Duan
Summary: This paper proposes a novel machine learning approach that can effectively extract harmful algal blooms (HABs) from images captured under various shooting poses. The approach was applied in Lake Chaohu and consistently reports the real-time status of HABs along the bank.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Spectroscopy
Jiang Xin-tong, Xiao Qi-tao, Li Yi-min, Liao Yuan-shan, Liu Dong, Duan Hong-tao
Summary: Lake Bosten, the largest inland freshwater lake in the northwest arid zone of China, has been heavily impacted by human activities and wastewater discharge, affecting the lake ecosystem and drinking water safety. The study analyzed the three-dimensional fluorescence spectra of coloured dissolved organic matter (CDOM) and found three fractions of CDOM in Lake Bosten. The influence of river input on Lake Bosten's dissolved organic matter (DOM) varied between seasons and correlated with the change in river water quality.
SPECTROSCOPY AND SPECTRAL ANALYSIS
(2023)
Article
Environmental Sciences
Yuanshan Liao, Qitao Xiao, Yimin Li, Chen Yang, Junli Li, Hongtao Duan
Summary: Saline lakes are integral components of the global carbon cycle and play a significant role in greenhouse gas emissions. This study focuses on Bosten Lake, an inland saline lake in China, and reveals that it is a significant source of atmospheric carbon emissions. The emissions are influenced by temporal variations in salinity and trophic state. Additionally, spatial heterogeneity in carbon emissions is driven by exogenous inputs. This study provides valuable insights into greenhouse gas emissions from saline lakes in arid regions and contributes to a better understanding of the carbon cycle in different types of lakes.
SCIENCE OF THE TOTAL ENVIRONMENT
(2024)
Article
Remote Sensing
Zhuting Tan, Zhengyu Tan, Juhua Luo, Hongtao Duan
Summary: This study proposes a new method for cotton sample selection and employs machine learning to effectively identify long time series cotton planting areas at a 30-meter resolution scale. The study uses Bortala and Shuanghe in Xinjiang, China as case studies to demonstrate the approach. The results show that the method can achieve high accuracy and reveal the spatiotemporal distribution characteristics of cotton planting areas.
GEO-SPATIAL INFORMATION SCIENCE
(2023)
Article
Biodiversity Conservation
Yinguo Qiu, Hao Liu, Fuzhang Liu, Dexin Li, Chengzhao Liu, Weixin Liu, Jiacong Huang, Qitao Xiao, Juhua Luo, Hongtao Duan
Summary: This study developed a novel framework that can timely and accurately grasp both present conditions and accumulation risks of harmful algal blooms (HABs) in nearshore areas of lakes. By using quantitative monitoring and simulation modeling, the framework showed high value in monitoring and emergency prevention of HABs.
ECOLOGICAL INDICATORS
(2023)
Article
Engineering, Electrical & Electronic
Chen Yang, Zhenyu Tan, Yimin Li, Ming Shen, Hongtao Duan
Summary: This article presents the performance of multiple machine learning (ML) algorithms in detecting algal blooms in Chinese eutrophic inland lakes. The random forest (RF) model stands out among the four tested ML models, achieving an overall accuracy above 0.90. Even with data from a single lake used as training samples, the RF model maintains a fairly high accuracy of 0.88 for other lakes. These ML models show promising potential for algal bloom detection across different lakes and provide practical references for further applications.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Ruonan Chen, Liangyun Liu, Xinjie Liu, Zhunqiao Liu, Lianhong Gu, Uwe Rascher
Summary: This study presents methods to accurately estimate sub-daily GPP from SIF in evergreen needleleaf forests and demonstrates that the interactions among light, canopy structure, and leaf physiology regulate the SIF-GPP relationship at the canopy scale.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Daniel L. Goldberg, Madankui Tao, Gaige Hunter Kerr, Siqi Ma, Daniel Q. Tong, Arlene M. Fiore, Angela F. Dickens, Zachariah E. Adelman, Susan C. Anenberg
Summary: A novel method is applied in this study to directly use satellite data to evaluate the spatial patterns of urban NOx emissions inventories. The results show that the 108 spatial surrogates used by NEMO are generally appropriate, but there may be underestimation in areas with dense intermodal facilities and overestimation in wealthy communities.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Zhuoyue Hu, Xiaoyan Li, Liyuan Li, Xiaofeng Su, Lin Yang, Yong Zhang, Xingjian Hu, Chun Lin, Yujun Tang, Jian Hao, Xiaojin Sun, Fansheng Chen
Summary: This paper proposes a whisk-broom imaging method using a long-linear-array detector and high-precision scanning mirror to achieve high-resolution and wide-swath thermal infrared data. The method has been implemented in the SDGs satellite and has shown promising test results.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Dandan Wang, Leiqiu Hu, James A. Voogt, Yunhao Chen, Ji Zhou, Gaijing Chang, Jinling Quan, Wenfeng Zhan, Zhizhong Kang
Summary: This study evaluates different schemes for determining model coefficients to quantify and correct the anisotropic impact from remote sensing LST for urban applications. The schemes have consistent results and accurately estimate parameter values, facilitating the broadening of parametric models.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Jamie Tolan, Hung - Yang, Benjamin Nosarzewski, Guillaume Couairon, Huy V. Vo, John Brandt, Justine Spore, Sayantan Majumdar, Daniel Haziza, Janaki Vamaraju, Theo Moutakanni, Piotr Bojanowski, Tracy Johns, Brian White, Tobias Tiecke, Camille Couprie
Summary: Vegetation structure mapping is crucial for understanding the global carbon cycle and monitoring nature-based approaches to climate adaptation and mitigation. This study presents the first high-resolution canopy height maps for California and Sao Paulo, achieved through the use of very high resolution satellite imagery and aerial lidar data. The maps provide valuable tools for forest structure assessment and land use monitoring.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Regina Eckert, Steffen Mauceri, David R. Thompson, Jay E. Fahlen, Philip G. Brodrick
Summary: In this paper, a mathematical framework is proposed to improve the retrieval of surface reflectance and atmospheric parameters by leveraging the expected spatial smoothness of the atmosphere. Experimental results show that this framework can reduce the surface reflectance retrieval error and surface-related biases.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Chongya Jiang, Kaiyu Guan, Yizhi Huang, Maxwell Jong
Summary: This study presents the Field Rover method, which uses vehicle-mounted cameras to collect ground truth data on crop harvesting status. The machine learning approach and remote sensing technology are employed to upscale the results to a regional scale. The accuracy of the remote sensing method in predicting crop harvesting dates is validated through comparison with satellite data.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Oksana V. Lunina, Anton A. Gladkov, Alexey V. Bochalgin
Summary: In this study, an unmanned aerial vehicle (UAV) was used to detect and map surface discontinuities with displacements of a few centimeters, indicating the presence of initial geological deformations. The study found that sediments of alluvial fans are susceptible to various tectonic and exogenous deformational processes, and the interpretation of ultra-high resolution UAV images can help recognize low-amplitude brittle deformations at an early stage. UAV surveys are critical for discerning neotectonic activity and its related hazards over short observation periods.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Feng Zhao, Weiwei Ma, Jun Zhao, Yiqing Guo, Mateen Tariq, Juan Li
Summary: This study presents a data-driven approach to reconstruct the terrestrial SIF spectrum using measurements from the TROPOMI instrument on Sentinel-5 precursor mission. The reconstructed SIF spectrum shows improved spatiotemporal distributions and demonstrates consistency with other datasets, indicating its potential for better understanding of the ecosystem function.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Stephen Stehman, John E. Wagner
Summary: This article investigates optimal sample allocation in stratified random sampling for estimation of accuracy and proportion of area in applications where the target class is rare. The study finds that precision of estimated accuracy has a stronger impact on sample allocation than estimation of proportion of area, and the trade-offs among these estimates become more pronounced as the target class becomes rarer. The results provide quantitative evidence to guide sample allocation decisions in specific applications.
REMOTE SENSING OF ENVIRONMENT
(2024)
Article
Environmental Sciences
Jingyao Zheng, Tianjie Zhao, Haishen Lu, Defu Zou, Nemesio Rodriguez-Fernandez, Arnaud Mialon, Philippe Richaume, Jianshe Xiao, Jun Ma, Lei Fan, Peilin Song, Yonghua Zhu, Rui Li, Panpan Yao, Qingqing Yang, Shaojie Du, Zhen Wang, Zhiqing Peng, Yuyang Xiong, Zanpin Xing, Lin Zhao, Yann Kerr, Jiancheng Shi
Summary: Soil moisture and freeze/thaw (F/T) play a crucial role in water and heat exchanges at the land-atmosphere interface. This study reports the establishment of a wireless sensor network for soil moisture and temperature over the permafrost region of Tibetan Plateau. Satellite-based surface soil moisture (SSM) and F/T products were evaluated using ground-based measurements. The results show the reliability of L-band passive microwave SSM and F/T products, while existing F/T products display earlier freezing and later thawing, leading to unsatisfactory accuracy.
REMOTE SENSING OF ENVIRONMENT
(2024)