Article
Plant Sciences
Weiwei Sun, Qijin He, Jiahong Liu, Xiao Xiao, Yaxin Wu, Sijia Zhou, Selimai Ma, Rongwan Wang
Summary: This study established a scalable annual and inter-annual quality prediction model for summer maize in different growth periods using hierarchical linear modeling (HLM) combined with hyperspectral and meteorological data. Compared to the multiple linear regression (MLR) using vegetation indices (VIs), the HLM showed improved prediction accuracy. The results demonstrated that meteorological factors, especially precipitation, had a significant influence on grain quality.
FRONTIERS IN PLANT SCIENCE
(2023)
Article
Environmental Sciences
Karina Dias-Silva, Thiago Bernardi Vieira, Talissa Pio de Matos, Leandro Juen, Juliana Simiao-Ferreira, Robert M. Hughes, Paulo De Marco Junior
Summary: The encroachment of agricultural activities into natural areas poses a growing problem for stream ecological condition. Measurements of stream ecological condition using both biotic and abiotic parameters are crucial, and physical-chemical measures of water quality have been widely used. Recent research has utilized physical habitat structure and catchment land use to better understand water body conditions. However, remote sensing of catchment land use and land cover alone may not be sufficient to predict stream water quality or habitat structure accurately.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Lennart Schmidt, David Schaefer, Juliane Geller, Peter Luenenschloss, Bert Palm, Karsten Rinke, Corinna Rebmann, Michael Rode, Jan Bumberger
Summary: This article introduces the software system SaQC for automated quality control, which transforms large volumes of raw data from environmental sensor networks into usable data for monitoring environmental changes and decision support. It focuses on achieving real-time data processing and improving data quality.
ENVIRONMENTAL MODELLING & SOFTWARE
(2023)
Article
Geochemistry & Geophysics
Debora M. Bayer, Fabio M. Bayer, Paolo Gamba
Summary: This study proposes a novel 3-D autoregressive model for analyzing multitemporal remote sensing image data, exploring correlations in three dimensions for filtering, prediction, and anomaly detection purposes. Experimental results demonstrate the significance of the model for interpreting spatiotemporal remote sensing data.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Xu Huang, Zhengwei He, Yan Wu, Pengyi Lyu
Summary: This study establishes a remote sensing image quality evaluation model using Rough Set Theory, Fuzzy Set Theory, and BP Neural Network theory, selects the best quality remote sensing images for specific applications, and proves the feasibility of the model through three different experiments.
Article
Environmental Sciences
Shi Bai, Jie Zhao
Summary: Geochemical data is widely used in mineral exploration, environmental assessment, and resource potential analysis. However, the spatial accuracy of geochemical data often limits decision-making. Harsh natural and geographic conditions make geochemical sampling difficult in some areas, resulting in medium/low-precision survey data that may not be adequate for regional mapping and exploration. The use of remote sensing technology can help address this issue.
Article
Geochemistry & Geophysics
Chen Xu, Xiaoping Du, Xiangtao Fan, Zhenzhen Yan, Xujie Kang, Junjie Zhu, Zhongyang Hu
Summary: This research analyzed the processing flow of remote sensing big data from the perspective of computer science and remote sensing science, proposing a modular framework. By introducing computation ready data as a dynamic data type to connect key modules of the framework, it significantly reduces experimental costs for remote sensing researchers.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Chandrabali Karmakar, Mihai Datcu
Summary: This research proposes a framework for interactive and interpretable visualization of remote sensing data using two machine learning models and an Elasticsearch (ES) database, offering researchers helpful insights into understanding how a model works.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Review
Environmental Sciences
Haibo Yang, Jialin Kong, Huihui Hu, Yao Du, Meiyan Gao, Fei Chen
Summary: Water pollution is a serious problem affecting water environments, resources, and human health. Remote sensing technology provides temporal and spatial advantages for water quality monitoring, but faces challenges in atmospheric correction, data resolution, and retrieval models.
Review
Environmental Sciences
Farzane Mohseni, Fatemeh Saba, S. Mohammad Mirmazloumi, Meisam Amani, Mehdi Mokhtarzade, Sadegh Jamali, Sahel Mahdavi
Summary: This paper reviews the application of remote sensing techniques in ocean water quality (OWQ) monitoring, introducing common OWQ parameters and monitoring techniques. The study finds that chlorophyll-a and colored dissolved organic matter are the dominant parameters for OWQ monitoring, and data from optical and passive microwave sensors are effective in estimating OWQ parameters.
MARINE ENVIRONMENTAL RESEARCH
(2022)
Article
Geochemistry & Geophysics
Jifa Guo, Shihong Du
Summary: This article proposes a novel multicenter supervised fuzzy classification method to model spectral diversity in multispectral remote sensing data. By clustering and labeling, it effectively improves classification accuracy and provides better representation for multiple centers of land cover types.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Weicheng Xu, Weiguang Yang, Pengchao Chen, Yilong Zhan, Lei Zhang, Yubin Lan
Summary: This study uses time-series UAV multispectral and RGB remote sensing images combined with machine learning to model four main quality indicators of cotton fibers. A deep learning algorithm is used to identify and extract cotton boll pixels in remote sensing images and improve the accuracy of quantitative extraction of spectral features. The prediction model can well predict the average length, uniformity index, and micronaire value of the upper half.
Article
Geography, Physical
Zhili Zhang, Qi Zhang, Xiangyun Hu, Mi Zhang, Dehui Zhu
Summary: Currently, object extraction from remotely sensed imagery heavily relies on annotated sample data, but most algorithms ignore the impact of unreliable annotations, leading to low-reliability solutions. To address this, we propose AQSNet, a network for automatic quality assessment of remote sensing annotated samples, which uses a multi-scale channel-spatial attention module to identify poor-quality annotations. We also introduce a simple method for generating effective training samples and a large-scale land cover dataset HBD41 for validation.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Yanxin Xi, Luyan Ji, Weitun Yang, Xiurui Geng, Yongchao Zhao
Summary: This article proposes four multi-target detection algorithms for multitemporal remote sensing data by combining filter tensor analysis with multiple target constraints, fully exploiting the time-series information. The experimental results show the effectiveness and superiority of the proposed methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Review
Environmental Sciences
Xixuan Zhou, Jinyu Wang, Fengjie Zheng, Haoyu Wang, Haitao Yang
Summary: This paper discusses the research progress related to data sources and extraction methods for remote sensing-based coastline extraction. It summarizes the suitability of data and extraction algorithms for specific coastline types, as well as the challenges and prospects in coastline data construction.
Correction
Geochemistry & Geophysics
Talib Oliver-Cabrera, Cathleen E. Jones, Zhang Yunjun, Marc Simard
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Gordon Ansel Nedd, Temitope D. Timothy Oyedotun, Marc Simard
Summary: Mangrove forests are crucial for coastal communities, but are threatened by urban development and sea-level rise due to climate change. To protect this ecosystem, the Government of Guyana has implemented a program of mangrove replanting and restoration. This study used synthetic aperture radar imagery to map mangrove regeneration and dynamics, and analyzed the biomass changes through the analysis of diameter and height of the mangroves.
EARTH SYSTEMS AND ENVIRONMENT
(2023)
Article
Water Resources
Charuleka Varadharajan, Alison P. Appling, Bhavna Arora, Danielle S. Christianson, Valerie C. Hendrix, Vipin Kumar, Aranildo R. Lima, Juliane Mueller, Samantha Oliver, Mohammed Ombadi, Talita Perciano, Jeffrey M. Sadler, Helen Weierbach, Jared D. Willard, Zexuan Xu, Jacob Zwart
Summary: The global decline in water quality in rivers and streams has created an urgent need for new watershed management strategies. Machine learning can aid in developing more accurate, computationally tractable, and scalable models for analyzing and predicting river water quality. When combined with decades of process understanding, machine learning has the potential to address water quality problems effectively.
HYDROLOGICAL PROCESSES
(2022)
Article
Limnology
Robert Ladwig, Alison P. Appling, Austin Delany, Hilary A. Dugan, Qiantong Gao, Noah Lottig, Jemma Stachelek, Paul C. Hanson
Summary: This study investigates the metabolism patterns of lakes in Wisconsin, USA, and compares the differences in metabolic trends between oligotrophic and eutrophic lakes. The results show that oligotrophic lakes have diverse metabolism patterns, while eutrophic lakes exhibit consistent long-term trends of increased oxygen consumption over the last decade. The landscape setting is identified as the primary driver of long-term metabolic change.
LIMNOLOGY AND OCEANOGRAPHY
(2022)
Article
Environmental Sciences
J. M. Sadler, A. P. Appling, J. S. Read, S. K. Oliver, X. Jia, J. A. Zwart, V Kumar
Summary: The study explores the benefits of using multi-task deep learning models to predict both streamflow and water temperature, and finds that it can lead to more accurate predictions for certain sites and model configurations.
WATER RESOURCES RESEARCH
(2022)
Article
Geosciences, Multidisciplinary
Xiao Yang, Catherine M. O'Reilly, John R. Gardner, Matthew R. Ross, Simon N. Topp, Jida Wang, Tamlin M. Pavelsky
Summary: This study used satellite images to determine the distribution of the modal water color of 85,360 representative lakes worldwide. The results showed a bimodal distribution of blue and non-blue lakes, with climate and lake morphology influencing the lake color. This study provides a critical baseline for understanding lake responses to global environmental change.
GEOPHYSICAL RESEARCH LETTERS
(2022)
Article
Ecology
Christian J. J. Thomas, Robert K. K. Shriver, Fabian Nippgen, Matthew Hepler, Matthew R. V. Ross
Summary: Mountaintop removal mining and other surface mining operations have significant impacts on Appalachia's communities and ecosystems. Despite legal mandates for restoration, the long-term outcomes of restoration efforts are uncertain. Research shows that post-mining forests are not recovering to a level consistent with unmined sites.
RESTORATION ECOLOGY
(2023)
Article
Environmental Sciences
Augusto Getirana, Sujay Kumar, Goutam Konapala, Wanshu Nie, Kim Locke, Bryant Loomis, Charon Birkett, Martina Ricko, Marc Simard
Summary: Satellite observations show that coastal Louisiana has experienced significant land loss in recent decades, which can be attributed to climate change and human activities. This study investigates the impacts of sea level rise and climate-induced hydrological change on flood risk in southern Louisiana and examines the effectiveness of water management through flood control structures. The findings reveal that climate-induced hydrological change has increased flood risk and population vulnerability, while water management interventions can mitigate these risks.
WATER RESOURCES RESEARCH
(2023)
Article
Environmental Sciences
John Gardner, Tamlin Pavelsky, Simon Topp, Xiao Yang, Matthew R. Ross, Sagy Cohen
Summary: Humans have significantly disrupted the global sediment cycle, affecting river morphology and ecosystems. Based on satellite observations from 1984 to 2018, the RivSed database provides a spatially explicit view of river sediment, revealing declining trends in sediment concentration in 32% of US rivers. Most rivers show decreasing sediment concentration downstream, primarily due to large dams. Comparing observations with models, there are differences in longitudinal sediment concentration patterns. RivSed has important implications for river geomorphology and ecology, illustrating human impacts on US river corridors.
ENVIRONMENTAL RESEARCH LETTERS
(2023)
Article
Multidisciplinary Sciences
Joan P. Casas-Ruiz, Pascal Bodmer, Kelly Ann Bona, David Butman, Mathilde Couturier, Erik J. S. Emilson, Kerri Finlay, Helene Genet, Daniel Hayes, Jan Karlsson, David Pare, Changhui Peng, Rob Striegl, Jackie Webb, Xinyuan Wei, Susan E. Ziegler, Paul A. del Giorgio
Summary: This Perspective presents an integrative framework to improve estimates of land-atmosphere carbon exchange by considering the accumulation of carbon in the landscape and its export through rivers. The framework uses the watershed as the fundamental spatial unit and integrates all terrestrial and aquatic ecosystems. The application of this framework can bridge the gap between land and atmosphere-based approaches and enhance communication and collaboration among research communities.
NATURE COMMUNICATIONS
(2023)
Article
Multidisciplinary Sciences
Spencer Rhea, Nicholas Gubbins, Amanda G. DelVecchia, Matthew R. Ross, Emily S. Bernhardt
Summary: The reliability of stream discharge estimates provided by NEON was evaluated using three approaches. It was found that 39% of the data met the highest quality criteria, 11% fell into an intermediate classification, and 50% of the data were classified as unreliable.
Article
Geosciences, Multidisciplinary
G. McNicol, E. Hood, D. E. Butman, S. E. Tank, I. J. W. Giesbrecht, W. Floyd, D. D'Amore, J. B. Fellman, A. Cebulski, A. Lally, H. McSorley, S. G. Gonzalez Arriola
Summary: The rivers in the northeast Pacific Coastal Temperate Rainforest export 3.5 Tg-C yr(-1) of dissolved organic carbon (DOC) to the ocean. Over 56% of this DOC flux comes from small coastal watersheds, which make up only 22% of the total drainage basin. The average DOC yield from these coastal watersheds is roughly three times higher than that from tropical regions worldwide. These findings suggest that the export of DOC from these watersheds plays a significant role in regional-scale heterotrophy within near-shore marine ecosystems in the northeast Pacific.
GEOPHYSICAL RESEARCH LETTERS
(2023)
Article
Environmental Sciences
Hannah D. Conroy, Erin R. Hotchkiss, Kaelin M. Cawley, Keli Goodman, Robert O. Hall Jr, Jeremy B. Jones, Wilfred M. Wollheim, David Butman
Summary: Headwater stream networks contribute significantly to the terrestrial carbon dioxide flux due to turbulence and interaction with terrestrial environments. Measuring and scaling these emissions is challenging due to limited monitoring points. Our study found that the stream network had higher carbon emissions under high flow conditions compared to low flow conditions. Winter stream emissions accounted for a larger percentage of the forest net ecosystem exchange than in summer, highlighting the importance of considering flow regime in annual estimates of stream network emissions.
JOURNAL OF GEOPHYSICAL RESEARCH-BIOGEOSCIENCES
(2023)
Article
Environmental Sciences
Chaopeng Shen, Alison P. P. Appling, Pierre Gentine, Toshiyuki Bandai, Hoshin Gupta, Alexandre Tartakovsky, Marco Baity-Jesi, Fabrizio Fenicia, Daniel Kifer, Li Li, Xiaofeng Liu, Wei Ren, Yi Zheng, Ciaran J. J. Harman, Martyn Clark, Matthew Farthing, Dapeng Feng, Praveen Kumar, Doaa Aboelyazeed, Farshid Rahmani, Yalan Song, Hylke E. E. Beck, Tadd Bindas, Dipankar Dwivedi, Kuai Fang, Marvin Hoge, Chris Rackauckas, Binayak Mohanty, Tirthankar Roy, Chonggang Xu, Kathryn Lawson
Summary: Differentiable modelling integrates the learning ability of machine learning with the interpretability of process-based models. It improves representation of processes, parameter estimation, and predictive accuracy in the geosciences. By connecting prior physical knowledge to neural networks, differentiable modelling combines process-based modelling and machine learning, offering better interpretability, generalizability, and extrapolation capabilities. It requires less training data compared to purely data-driven machine learning and scales well with increasing data volumes. Under data-scarce scenarios, it outperforms machine-learning models in capturing short-term dynamics and decadal-scale trends due to the imposed physical constraints.
NATURE REVIEWS EARTH & ENVIRONMENT
(2023)
Article
Environmental Sciences
L. Cortese, D. J. Jensen, M. Simard, S. Fagherazzi
Summary: Vegetation plays a crucial role in controlling soil accretion in coastal wetlands, and the Normalized Difference Vegetation Index (NDVI) can be used to monitor wetland health and degradation. This study used NDVI time-series and in situ measurements to develop models for mapping organic mass accumulation rates and salinity in Terrebonne Bay, Louisiana, USA.
JOURNAL OF GEOPHYSICAL RESEARCH-BIOGEOSCIENCES
(2023)