Review
Plant Sciences
Martha M. Farella, Joshua B. Fisher, Wenzhe Jiao, Kesondra B. Key, Mallory L. Barnes
Summary: This study emphasizes the untapped potential of remote sensing in plant ecology. Remote sensing in the thermal infrared domain can provide valuable information on plant behavior and stress conditions. It can evaluate plant species, traits, and structure, and offer unique insights into species distribution and phenology under changing climate conditions. Integrated understanding of processes and technology is crucial for scaling leaf traits, canopy structure, and regional patterns. The synergies between thermal remote sensing and other data sources provide a timely opportunity for ecologists to advance their understanding of plant physiology, ecology, and biogeography.
JOURNAL OF ECOLOGY
(2022)
Article
Environmental Sciences
Mukhtar Abubakar, Andre Chanzy, Guillaume Pouget, Fabrice Flamain, Dominique Courault
Summary: Conventional methods of crop mapping rely on ground truth information, but using satellite observations for time series analysis can accurately identify crops. This approach was successfully applied to identify irrigated permanent grasslands in the Crau area of Southern France, achieving good classification results.
Article
Environmental Sciences
Rohit Nandan, Varaprasad Bandaru, Jiaying He, Craig Daughtry, Prasanna Gowda, Andrew E. Suyker
Summary: The study evaluated the performance of various methods on two geographically distant locations and crops, finding that parametric methods generally outperformed others, while non-parametric methods showed moderate accuracy due to a smaller number of training observations.
Article
Environmental Sciences
Jinnuo Zhang, Dongdong Ma, Xing Wei, Jian Jin
Summary: Remote sensing coupled with hyperspectral technology is increasingly used to study plant growth, health, and productivity. However, diurnal variations in spectral characteristics introduce more data variance, compromising the performance of trait estimation models. In this study, a fixed gantry platform was used to capture VNIR hyperspectral images of corn canopies at consecutive time intervals. Diurnal calibration models were established at every wavelength, and using diurnal calibration in canopy spectra processing effectively reduced spectral variance brought about by varying imaging time.
Article
Agriculture, Multidisciplinary
Shay Adar, Marcelo Sternberg, Eli Argaman, Zalmen Henkin, Guy Dovrat, Eli Zaady, Tarin Paz-Kagan
Summary: This article presents a new Pasture Quality Index (PQI) that can evaluate the nutritional quality of pastures and prevent pasture degradation. The authors developed the model using satellite data, plant samples, and pasture quality analysis, and established statistical models using ground truth data and satellite reflectance values. The study found that pasture quality is closely related to seasonality and grazing patterns, with higher quality during mid-growth and in grazed areas.
AGRICULTURE ECOSYSTEMS & ENVIRONMENT
(2023)
Article
Environmental Sciences
Zhijie Liu, Pengju Guo, Heng Liu, Pan Fan, Pengzong Zeng, Xiangyang Liu, Ce Feng, Wang Wang, Fuzeng Yang
Summary: The study successfully predicted the leaf area index of different types of apple trees using multispectral remote-sensing data collected with drones and field measurements. Models of support vector regression (SVR) and gradient-boosting decision trees (GBDT) were trained, with the GBDT model demonstrating the best performance in terms of accuracy.
Article
Ecology
Demei Zhao, Jianing Zhen, Yinghui Zhang, Jing Miao, Zhen Shen, Xiapeng Jiang, Junjie Wang, Jincheng Jiang, Yuzhi Tang, Guofeng Wu
Summary: This study investigated the combined use of a radiative transfer model and a machine-learning model to estimate mangrove Leaf Area Index (LAI) using remote sensing images from different satellite sensors. The results showed that the Zhuhai-1 image had the best estimation accuracy, and newly developed three-band Vegetation Indices (VIs) proved effective in estimating mangrove LAI. Moreover, elevation and species composition were found to greatly influence the spatial distribution of mangrove LAI.
REMOTE SENSING IN ECOLOGY AND CONSERVATION
(2023)
Article
Optics
Anan Xu, Fang Wang, Liang Li
Summary: This study used UAV remote sensing to extract vegetation information in karst areas. By using the visible band and calculating the normalized vegetation index, combined with the spectral characteristics of the investigated plants, the vegetation information of the study area was obtained. The results showed that the proposed method has higher extraction accuracy and better effect than existing methods, providing a more efficient and targeted approach for vegetation research in complex terrain areas.
Article
Environmental Sciences
Mengyuan Xu, Yachun Mao, Mengqi Zhang, Dong Xiao, Hongfei Xie
Summary: This paper proposes a method of TFE detection based on reflectance spectroscopy and remote sensing. Experimental results show that the proposed method has superior accuracy in comparison to other algorithms. Furthermore, a remote sensing model using Sentinel-2 data is established to detect and plot the distribution of TFE in the mining area, providing assistance for the mining plan.
Review
Environmental Sciences
Tawanda W. Gara, Parinaz Rahimzadeh-Bajgiran, Roshanak Darvishzadeh
Summary: This review paper discusses the current state and potential approaches of remote sensing of leaf mass per area (LMA) in forest ecosystems, along with the challenges associated with LMA estimation. It also explores the physiological and environmental factors influencing spatial and temporal variation of LMA, as well as the scaling of LMA using remote sensing systems at different scales. The paper identifies future opportunities involving the synergy of multiple sensors and the utility of hybrid models for LMA estimation at canopy and landscape levels.
Article
Remote Sensing
Rajeev Bhattarai, Parinaz Rahimzadeh-Bajgiran, Aaron Weiskittel, Saeid Homayouni, Tawanda W. Gara, Ryan P. Hanavan
Summary: This study used multiple remote sensing data to model the leaf area index and basal area per ha of red spruce and balsam fir. The results showed that the Random Forest algorithm performed better in modeling. The red-edge spectral vegetation indices played a significant role in the estimation of both leaf area index and basal area per ha. These models are important for evaluating the dynamics of the eastern spruce budworm, as red spruce and balsam fir are its primary host species.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Chemistry, Multidisciplinary
Ruichang Li, Gangyi Zou, Liangjie Feng, Xuewu Fan
Summary: The design of a dual-band integrated space telescope system for visible light and long-wave infrared is proposed in this paper, which can simultaneously image two different bands with the ability to freely switch between them. The system is based on a coaxial reflection design with separate field of view for the two bands, achieving high imaging quality.
APPLIED SCIENCES-BASEL
(2021)
Article
Environmental Sciences
Huizeng Liu, Xianqiang He, Qingquan Li, Susanne Kratzer, Junjie Wang, Tiezhu Shi, Zhongwen Hu, Chao Yang, Shuibo Hu, Qiming Zhou, Guofeng Wu
Summary: The study proposes a hybrid approach for estimating UV Rrs from visible bands and evaluates its performance using in situ and satellite data, showing high accuracy in both clear open ocean and optically complex waters. The model-estimated UV Rrs may improve the accuracy of absorption coefficients in semi-analytical IOPs algorithm, indicating great potential for reconstructing UV Rrs data and enhancing IOPs retrieval for historical satellite sensors.
REMOTE SENSING OF ENVIRONMENT
(2021)
Review
Agriculture, Multidisciplinary
Christoph Stumpe, Joerg Leukel, Tobias Zimpel
Summary: Accurate prediction of biomass yield is crucial for decision-making in pasture management. The advancement of machine learning and optical sensing data has expanded the possibilities for monitoring and predicting pasture growth. This review examines the adoption of machine learning-based optical sensing techniques for predicting biomass yield in managed grasslands and provides recommendations for future research and reporting.
PRECISION AGRICULTURE
(2023)
Article
Environmental Sciences
Lida Andalibi, Ardavan Ghorbani, Mehdi Moameri, Zeinab Hazbavi, Arne Nothdurft, Reza Jafari, Farid Dadjou
Summary: The leaf area index (LAI) was evaluated in Ardabil Province, Iran, using a combination of remote sensing data from Google Earth Engine and traditional measurements, providing important insights for the management of ecosystems in the region.
Article
Water Resources
Isabelle Braud, Veronique Chaffard, Charly Coussot, Sylvie Galle, Patrick Juen, Hugues Alexandre, Philippe Baillion, Annick Battais, Brice Boudevillain, Flora Branger, Guillaume Brissebrat, Remi Cailletaud, Gerard Cochonneau, Remy Decoupes, Jean-Christophe Desconnets, Arnaud Dubreuil, Juliette Fabre, Santiago Gabillard, Marie-Francoise Gerard, Sylvain Grellet, Agnes Herrmann, Olivier Laarman, Eric Lajeunesse, Genevieve Le Henaff, Olivier Lobry, Antony Mauclerc, Jean-Baptiste Paroissien, Marie-Claire Pierret, Norbert Silvera, Herve Squividant
Summary: The French Critical Zone research infrastructure, OZCAR-RI, has developed a common information system, Theia/OZCAR IS, to make the in situ observations from its 20 observatories FAIR. The system's architecture was designed after consultation with users, data producers, and IT teams, and includes a common data model and controlled vocabulary.
HYDROLOGICAL SCIENCES JOURNAL
(2022)
Article
Environmental Sciences
Wei Zhang, Ping Tang, Thomas Corpetti, Lijun Zhao
Summary: This study proposes a weak-to-strong supervised learning framework for remote sensing land cover classification when insufficient pixel-level labeled datasets are available. The framework utilizes a small number of points with true class labels for training and progressively increases pixel-level supervision to improve the accuracy of the segmentation model. Experimental results show that the proposed framework outperforms other methods and is highly recommended for land cover classification tasks.
Article
Environmental Sciences
Xing Jin, Ping Tang, Thomas Houet, Thomas Corpetti, Emilien Gence Alvarez-Vanhard, Zheng Zhang
Summary: This paper proposes a deep learning method called separable convolution network for sequence image interpolation, which effectively produces high-quality time-series interpolated images and better simulates non-linear image data information.
Article
Environmental Sciences
Jiwen Tang, Damien Arvor, Thomas Corpetti, Ping Tang
Summary: The paper proposes a new method to detect the precise shape of center pivot irrigation systems by combining deep learning with real-time object detection network, image classification model, and accurate shape detection. Experimental results demonstrate the high precision and recall of the proposed method.
Article
Multidisciplinary Sciences
Jean-Pascal Matteau, Paul Celicourt, Guillaume Letourneau, Thiago Gumiere, Christian Walter, Silvio J. Gumiere
Summary: The study found that precision irrigation thresholds have an impact on the decomposition rate of SOC, particularly during the second quarter of the growing season, between 38 and 53 days after planting.
SCIENTIFIC REPORTS
(2021)
Article
Soil Science
Kevin Hoeffner, Hoel Hotte, Daniel Cluzeau, Xavier Charrier, Francois Gastal, Guenola Peres
Summary: Introducing grassland into annual crop rotations significantly increases earthworm abundance, biomass, and diversity, especially for anecic species. Grassland duration and fertilisation can increase earthworm abundance and biomass, particularly for anecic species, without affecting endogeic species and earthworm diversity. Increasing fertilisation leads to higher forage production, while duration of grassland does not have a significant effect on production.
APPLIED SOIL ECOLOGY
(2021)
Article
Environmental Sciences
Iris de Gelis, Sebastien Lefevre, Thomas Corpetti
Summary: In the context of rapid urbanization, monitoring the evolution of cities is crucial. This study compared six methods for urban 3D change detection, finding that deep learning methods highly depend on the size of the training set, while conventional machine learning methods exhibit stable results but have low transfer learning capacities.
Article
Environmental Sciences
Mathilde Letard, Antoine Collin, Thomas Corpetti, Dimitri Lague, Yves Pastol, Anders Ekelund
Summary: This article demonstrates the relevance of topobathymetric lidar data for coastal and estuarine habitat mapping by classifying bispectral data to produce high-resolution 3D maps. The combination of green waveform features, infrared intensities, and elevations yields the best classification results, achieving an accuracy of 90.5%.
Proceedings Paper
Acoustics
Binh Minh Nguyen, Ganglin Tian, Minh-Triet Vo, Aurelie Michel, Thomas Corpetti, Carlos Granero-Belinchon
Summary: This paper introduces a deep learning-based algorithm, Multi-residual U-Net, for improving the resolution of MODIS LST images. The proposed algorithm performs well in the task of super-resolving LST images.
2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022)
(2022)
Proceedings Paper
Geography, Physical
M. Letard, A. Collin, D. Lague, T. Corpetti, Y. Pastol, A. Ekelund
Summary: Topo-bathymetric lidar is efficient in mapping coastal habitats by collecting data over land-water interfaces. This study proposes a point-based approach using bispectral waveforms and machine learning to classify coastal habitats into 17 land and sea covers, achieving an overall accuracy of 86%.
XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III
(2022)
Proceedings Paper
Geography, Physical
I de Gelis, Z. Bessin, P. Letortu, M. Jaud, C. Delacourt, S. Costa, O. Maquaire, R. Davidson, T. Corpetti, S. Lefevre
Summary: This article discusses the issue of coastal cliff erosion and the use of machine learning methods to detect and categorize changes in the cliffs. Through studying the Petit Ailly cliffs in Varengeville-sur-Mer, France, the results show promising potential for this method.
XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III
(2022)
Article
Engineering, Electrical & Electronic
Hoang-An Le, Florent Guiotte, Minh-Tan Pham, Sebastien Lefevre, Thomas Corpetti
Summary: This article proposes a data-driven method to directly extract digital terrain models from airborne laser scanning point clouds. By collecting a large-scale dataset and conducting experiments, the effectiveness of this method is demonstrated, providing important references for research in the field of airborne laser scanning.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Review
Environmental Sciences
Emilien Alvarez-Vanhard, Thomas Corpetti, Thomas Houet
Summary: Unmanned aerial vehicles (UAVs) and satellite constellations are both crucial Earth Observation (EO) systems for monitoring land surface dynamics, offering unique advantages in terms of data acquisition and resolution. While data fusion is a well-known technique to exploit their synergies, specific strategies for integrating UAV and satellite data sources need to be further explored and formalized for various applications.
SCIENCE OF REMOTE SENSING
(2021)
Article
Multidisciplinary Sciences
Fabien Goge, Laurent Thuries, Youssef Fouad, Nathalie Damay, Fabrice Davrieux, Geraud Moussard, Caroline Le Roux, Severine Trupin-Maudemain, Matthieu Vale, Thierry Morvan
Summary: NIR spectroscopy combined with multivariate calibration methods is an effective analytical approach for predicting chemical contents of organic products. However, performance of the calibration model may decrease when data are acquired with different spectrometers. To overcome this limitation, standardization methods such as the PDS algorithm can be used. The dataset in this study includes samples from poultry and cattle manure in France and Reunion Island, which can be used to train and test chemometric models.
Article
Environmental Sciences
Y. Sim Tang, Chris R. Flechard, Ulrich Daemmgen, Sonja Vidic, Vesna Djuricic, Marta Mitosinkova, Hilde T. Uggerud, Maria J. Sanz, Ivan Simmons, Ulrike Dragosits, Eiko Nemitz, Marsailidh Twigg, Netty van Dijk, Yannick Fauvel, Francisco Sanz, Martin Ferm, Cinzia Perrino, Maria Catrambone, David Leaver, Christine F. Braban, J. Neil Cape, Mathew R. Heal, Mark A. Sutton
Summary: A comprehensive European dataset on monthly atmospheric NH3, acid gases, and aerosols was analyzed, revealing significant variations in concentrations of different gas and aerosol components between regions, countries, and ecosystem types.
ATMOSPHERIC CHEMISTRY AND PHYSICS
(2021)