<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Remote Sensing | Remote Sensing Time Series Analysis section | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/remote-sensing/sections/remote-sensing-time-series-analysis</link>
        <description>RSS Feed for Remote Sensing Time Series Analysis section in the Frontiers in Remote Sensing journal | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-05-13T23:06:25.645+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1737953</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1737953</link>
        <title><![CDATA[Recording seagrass growth in Mosquito Lagoon, Florida after Hurricanes Ian and Nicole]]></title>
        <pubdate>2026-04-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Stephanie A. Insalaco</author><author>Hannah V. Herrero</author><author>Hailey F. Vickich</author><author>Dominic B. Mashak</author>
        <description><![CDATA[Hurricanes Ian and Nicole hit Mosquito Lagoon, Florida in the Fall of 2022 and since then, the ecosystem has greatly shifted. Prior to these storm events, seagrass in Mosquito Lagoon was almost non-existent due to poor ecosystem conditions but made a rapid recovery in 2023. To study this change, a Random Forest Classification was implemented using Harmonized Landsat Sentinel imagery semi-monthly from September 2022 to January 2024. A model was created for each date in the period, and it was evident that while seagrass was still in a significant decline until March 2023, it came back to pre-collapse levels in summer 2023 and beyond. This recovery could be linked with the hurricane events as they would have redistributed seagrass fragments throughout the lagoon to promote previously dormant growth and altered water conditions, but more research is necessary to determine why exactly seagrass has recovered to this extent. Seagrass density varied throughout each date, with the lowest observed being 0% density and peak being 20.32%, as well as the accuracy of each model (average 84%) depending on the amount of seagrass present. This method was successful in identifying seagrass in limited quantities, and this study raises awareness that constant seagrass monitoring is needed in Mosquito Lagoon to promote conservation of the ecosystem.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1786848</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1786848</link>
        <title><![CDATA[Study of the changes in the Curonian Lagoon shoreline strip (1995–2024), Lithuania]]></title>
        <pubdate>2026-03-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Sérgio Lousada</author><author>Dainora Jankauskienė</author><author>Giedrė Ivavičiūtė</author><author>Lina Kuklienė</author><author>Indrius Kuklys</author><author>Birutė Ruzgienė</author><author>Vivita Pukite</author>
        <description><![CDATA[Coastal lagoons are among the most vulnerable aquatic environments to climate change and human pressures; therefore, studying the Curonian Lagoon is crucial to support evidence-based management and improve understanding of shoreline responses to hydro-meteorological forcing and local land-use pressures. This research investigates the evolution of the Curonian Lagoon shoreline near Preila (Neringa municipality) from 1995 to 2024 using a multi-temporal orthophotographic series (ORT10LT) complemented by a very high-resolution UAV orthomosaic produced in 2024. Shoreline position was consistently delineated and compared across eight observation periods to quantify section-based displacement and hotspot area changes. The analysis reveals a spatially organized pattern, with a persistent accumulation-prone stretch in the mid-profile (250–350 m) and a persistent erosion hotspot toward the latter shoreline (400–566 m). The maximum shoreline retreat reached 32.80 m (425 m section, 2024 relative to 1995–1999), while the maximum shoreline advance reached 18.22 m (275 m section, 2021–2023). Area-based hotspot metrics indicate erosion losses up to 654 m2 (2018–2020) and accumulation gains up to 395 m2 (2009–2010) relative to the baseline. These results provide a reproducible, decision-oriented shoreline-change characterization that supports targeted monitoring and management of this culturally and environmentally significant lagoon margin.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1659305</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1659305</link>
        <title><![CDATA[Mapping small-sized logging disturbances in tropical forests using Sentinel-1 time series and an extensive ground truth dataset]]></title>
        <pubdate>2026-03-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Audrey Mercier</author><author>Julie Betbeder</author><author>Frédéric Mortier</author><author>Nicolas Barbier</author><author>Pierre Ploton</author><author>Guillaume Cornu</author><author>Pierre Couteron</author>
        <description><![CDATA[Deforestation and forest degradation are the main threats to biodiversity and carbon stocks in tropical forests. Advances in optical and SAR satellite sensors have enabled the development of real-time monitoring of deforestation on a global scale. SAR is particularly appealing in tropical areas due to its insensitivity to cloud cover. However, the automatic detection of small disturbed areas (such as individual tree felling gaps) remains a major challenge. Thanks to a unique dataset consisting of 23,759 locations of individual tree felling gaps and multi-date drone lidar acquisitions, we evaluated the potential of Sentinel-1 dense time series for monitoring small-sized forest disturbances substantially smaller than 0.1 ha on both FSC-certified and artisanal logging sites in the Congo Basin. We designed a new method for forest monitoring using the fused-lasso technique optimized to detect abrupt changes of at least 0.02 ha in Sentinel-1 time series using the fused-lasso technique (Fused-Lasso Change Detection, FLCD). We assessed our new method along with the Cumulative Sum (CuSum) that also proved promising for detecting small impacts, referring for the first time to precise disturbance dates over large areas. Both approaches reached similar rates of confirmed felling gaps that were similarly increasing with gap size, and similar rates of unconfirmed detected gaps. The FLCD method estimates the dates of tree felling more accurately in FSC-certified areas (−2 days difference for FLCD and −19 for CuSum on average). The effective resolution of the S-1 images limits detection for the smallest gaps, yet the approach can help detect and monitor degradation fronts. Fused lasso regression is relevant for modeling the temporal trajectories of the radar signal, which will allow taking advantage of both the increasing availability of UAV-borne data and the lengthening of the S-1 image series.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1782148</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1782148</link>
        <title><![CDATA[Crop type mapping in the pre-Sentinel era using variable-length Landsat time-series and self-supervised learning]]></title>
        <pubdate>2026-02-20T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Jayan Wijesingha</author><author>Ilze Beila</author>
        <description><![CDATA[Crop type mapping is crucial for agricultural land cover monitoring and decision-making. State-of-the-art methods developed using recent Sentinel satellite data have already demonstrated their ability to accurately map crop types. However, crop type mapping for the pre-Sentinel era remains challenging due to the limited availability of higher spatial- and temporal-resolution data. This study addresses this knowledge gap by leveraging variable-length Landsat satellite time-series (L-SITS) data in combination with a self-supervised learning model, SITS-BERT, for crop type mapping. This case study, conducted in two German districts, demonstrates the potential of mapping two different crop type levels (CTL1 - 5 and CTL2 - 9 classes) in the pre-Sentinel era. The SITS-BERT model, pre-trained on unlabelled L-SITS data, was fine-tuned on single-year and 3-year datasets and evaluated using past and future years’ data, compared with the model’s training data. The SITS-BERT model achieved overall accuracies of 0.78–0.83 and 0.64–0.76 for CTL1 and CTL2, respectively, with fine-tuning on single-year data. The model fine-tuned with 3 years achieved higher accuracies (0.81–0.85 and 0.72–0.78). The results showed that the SITS-BERT model finetuned with single-year data outperforms the baseline random forest model trained on single-year fixed-length L-SITS data. The study highlighted that, with this approach, limited number of available SITS observations can still be useful. The findings of this study demonstrated the potential of the SITS-BERT model with L-SITS data for crop-type mapping in the pre-Sentinel era, contributing to a more comprehensive understanding of agricultural land cover dynamics and to the evaluation of agricultural policy impacts.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1723667</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1723667</link>
        <title><![CDATA[Evaluating the efficacy of hybrid deep learning models in assessing temporal night-time light trends for the cities of Cape Town, Durban and Johannesburg in South Africa]]></title>
        <pubdate>2026-01-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Zandile Mncube</author><author>Sifiso Xulu</author><author>Nkanyiso Mbatha</author>
        <description><![CDATA[IntroductionIncreasing research demonstrates the value of nighttime light (NTL) data for studying human activities, including urban change. The public availability of these products on geospatial computing platforms like Google Earth Engine (GEE) has expanded their use for various applications and adding incorporation of Python and R analysis tools.MethodsDeep learning techniques such as Wavelet Denoise (WD), Empirical Mode Decomposition (EMD), and Enhanced Empirical Mode Decomposition (EEMD) are seldom used in NTL research, but here were used them with long short-term memory (LSTM) to form hybrid models to denoise and decompose NTL trajectory to interpretable frequency levels and intrinsic mode functions (IMFs) that improve trend evaluation. We leveraged these tools to assess the performance of deep learning models in modelling and forecasting NTL trends in Cape Town, Durban, and Johannesburg from 2014 to 2023. Root mean square error (RMSE) and mean absolute error (MAE) were used to evaluate model performance.ResultsThe findings indicate that integrating decomposition approaches with LSTM enhances the precision and interpretability of NTL modelling. In Cape Town, the RMSE for all models varied from 0.083 to 0.114, while the MAE ranged from 0.063 to 0.085. Durban, RMSE ranged from 0.069 to 0.133, and MAE varied from 0.055 to 0.108. Johannesburg, RMSE ranged from 0.124 to 0.449 and MAE varied from 0.102 to 0.383.DiscussionBecause of decomposition advantages, EEMD-LSTM hybrid model showing superior efficacy in Cape Town and Johannesburg, whilst EMD-LSTM model excelled in Durban.ConclusionFrom the findings we can conclude that these models can enhance NTL analysis.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1705386</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1705386</link>
        <title><![CDATA[Terrestrial ecosystems are in transition]]></title>
        <pubdate>2025-11-26T00:00:00Z</pubdate>
        <category>Mini Review</category>
        <author>Huan Wang</author><author>Yuchao Yan</author><author>Delong Li</author><author>Xiaojun Li</author><author>Xiangzhuo Liu</author><author>Lei Fan</author><author>Mengjia Wang</author><author>Ying Yao</author><author>Yiling Cai</author><author>Shijie Yan</author><author>Zanpin Xing</author><author>Yi Zheng</author><author>Yuqing Liu</author><author>Jean-Pierre Wigneron</author>
        <description><![CDATA[Global climate change and accelerating human disturbance may trigger biosphere tipping points across a range of scales and push the terrestrial ecosystem undergoing irreversible critical transitions toward alternative ecosystems. The resilience of these systems—their capacity to resist and recover from perturbations and maintain structure and function—is being eroded by multiple drivers, including land-use change, altered disturbance regimes, and biogeochemical imbalances. These drivers interact in nonlinear ways, generating cascading effects across scales and amplifying the risk of state shifts. Increasing evidence based on remote sensing time series shows that many forests are losing resilience, suggesting an early warning signal for approaching tipping points. Once tipping points are crossed, recovery is highly uncertain or even impossible on human timescales, with profound implications for biodiversity, ecosystem services, and the global carbon cycle. Understanding the mechanisms of resilience loss and identifying early-warning signals of approaching thresholds are therefore central to predicting future ecosystem stability. Due to its ability to monitor key parameters related to vegetation dynamics, remote sensing has emerged as a key tool for monitoring vegetation resilience. This can be done over large areas and with high spatial (about 10 m) and temporal (week-month) resolutions. This review synthesizes current advances on the drivers, evidence, tipping dynamics of terrestrial ecosystems in transition, and advantages of remote sensing in resilience study. We further highlight urgent action to anticipate and manage critical risks, and mitigate climate change in the Anthropocene.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1744233</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1744233</link>
        <title><![CDATA[Correction: Monitoring the dual-season hydrological dynamics of the Pong reservoir in Himachal Pradesh, India]]></title>
        <pubdate>2025-11-18T00:00:00Z</pubdate>
        <category>Correction</category>
        <author>Frontiers Production Office </author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1682140</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1682140</link>
        <title><![CDATA[Monitoring the dual-season hydrological dynamics of the Pong reservoir in Himachal Pradesh, India]]></title>
        <pubdate>2025-11-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Rajesh Sarda</author><author>Pankaj Kumar</author>
        <description><![CDATA[Reservoir hydrological conditions play a crucial role in both natural and human ecosystems. This study investigates the dual-season (pre-monsoon and post-monsoon) hydrological dynamics of the Pong Reservoir and analyzing the spatial character using Landsat multi-spectral images collected from 1994 to 2024. The 30 years were divided into three phases to assess changes in hydrological consistency and relative water depth over time. The Modified Normalized Difference Water Index (MNDWI) proved effective for mapping the water coverage area of the Pong Reservoir. Analysis based on MNDWI indices reveals significant seasonal fluctuations in water coverage, with 36.18 km2 of the reservoir exhibiting seasonal characteristics. Furthermore, the phase-wise results indicate a substantial decline in the area of high hydrological consistency during the pre-monsoon season, from 120.54 km2 in Phase 1 (1994–2004) to 88.49 km2 in Phase 3 (2015–2024). The change matrix indicates that 10.62 km2 transformed from higher to lower hydrological consistency classes from Phase 1 to Phase 2, and a further 51.97 km2 underwent a similar transformation from Phase 2 to Phase 3 in the post-monsoon season. The study employed a spatial linear trend modelling approach to identify trends in relative water depth, revealing a decreasing trend and a quantifiable reduction in the reservoir’s depth for both seasons. Additionally, further analysis was conducted on the impact of seasonal rainfall and sedimentation on the hydrological dynamics of the Pong Reservoir. These findings could assist policymakers in formulating effective conservation plans for this important Ramsar site.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1639845</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1639845</link>
        <title><![CDATA[Assessing antecedent climatic and hydrological conditions and anthropogenic impacts to drive catastrophic flooding in the northeastern United States]]></title>
        <pubdate>2025-09-30T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Aashutosh Aryal</author><author>Venkataraman Lakshmi</author>
        <description><![CDATA[The northeastern US has been experiencing catastrophic flooding in recent years. Flooding in the region is occurring more frequently and with higher intensity, causing substantial economic losses. The flooding may be caused by changes in climatic and hydrological drivers such as extreme precipitation, rapid snowmelt, and saturated soil moisture conditions, along with impacts from human-driven interventions like changes in land cover and urban imperviousness. This study analyzes the abovementioned variables to indicate flood risk and understand whether they contribute to flooding in the Northeastern US region. This study utilized various remote sensing satellite products for analyzing variables to fulfil the study’s objectives, wherever possible, such as Terra Moderate Resolution Imaging Spectroradiometer (MODIS) maximum snow cover extent, Soil Moisture Active Passive (SMAP) soil moisture, Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) precipitation, North American Land Change Monitoring System (NALCMS) land cover, and National Land Cover Database (NLCD) urban imperviousness. The region experienced wetter antecedent soil moisture conditions (>0.5 m3/m3) during spring due to rapid snowmelt (seasonal decline of ∼97%) in all the periods considered in the study. Moreover, the summer precipitation fed excess water (∼50–60 mm more rainfall than the decadal average) into wetter ground conditions, overwhelming the region’s overall hydrology and water balance and causing significant flooding. In addition, ∼1,838 sq. km. of croplands and ∼1,363 sq. km. of forests transitioned into built-up areas in a decade, increasing impervious surface and further exacerbating flooding risk in the region.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1611517</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1611517</link>
        <title><![CDATA[MODIS surface reflectance reconstruction based on an RTLSR inversion strategy with dynamically adjusted multi-surface parameters]]></title>
        <pubdate>2025-07-09T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Junjie Hu</author><author>Bo Gao</author><author>Hao Ma</author><author>Huili Gong</author><author>Yuanyuan Liu</author><author>Jiahao Liu</author><author>Yinchuan Feng</author><author>Heping Lin</author><author>Ziteng Wang</author>
        <description><![CDATA[IntroductionTo address the spatiotemporal discontinuities in Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance time series caused by cloud contamination, snow cover, and sensor limitations, this study proposes an an optimized RTLSR inversion strategy with dynamiclly adjusted of multi-surface parameters.MethodsThe method specifically aims to improve surface reflectance reconstruction accuracy in seasonally snow-covered regions and regions with significant vegetation phenological changes. To enhance the quality control of input data, the conventional NDVI threshold-based snow masking approach was replaced with the more rigorous “Internal Snow Mask” from the MOD09GA product. Additionally, vegetation indices exhibiting higher saturation resistance—namely the Enhanced Vegetation Index (EVI) and Leaf Area Index (LAI)—were adopted in place of NDVI to better characterize surface reflectance variations during significant phenological transitions.ResultsExperiments conducted in East and South Asia show that in seasonally snow-covered regions (e.g., eastern Tibetan Plateau and parts of northern Asia), RMSE reductions of 5.8%–7.1% are achieved in visible bands (Band1, Band3, Band4). Across the entire study area, the average RMSE across all MODIS bands (Band1–7) is reduced by 4.5%, with notable improvements in vegetation-sensitive near-infrared bands: Band2 and Band5 exhibit RMSE decreases of 14.3% and 6.3%, respectively. Compared with the MCD43A1 product, the proposed method demonstrates superior spatiotemporal continuity in mid- to low-latitude monsoon regions during summer and autumn, achieving a 9.77% increase in annual data availability.DiscussionThese results indicate that the improved approach effectively fills gaps in surface reflectance time series in persistently cloudy regions and offers a reliable complementary solution to existing MODIS products.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1588387</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1588387</link>
        <title><![CDATA[Integrating MODIS-derived indices for eucalyptus stand volume estimation: an evaluation of MODIS gross primary productivity]]></title>
        <pubdate>2025-05-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Manizheh Rajab Pourrahmati</author><author>Guerric Le Maire</author><author>Nicolas Baghdadi</author><author>Clayton Alcarde Alvares</author><author>José Luis Stape</author><author>Henrique Ferraco Scolforo</author><author>Otávio Camargo Campoe</author><author>Yann Nouvellon</author><author>Joannès Guillemot</author>
        <description><![CDATA[Accurate estimates of stand volume dynamics in Eucalyptus plantations is critical for sustainable forest management and wood production. This study investigates the integration of MODIS-derived indices, such as gross primary productivity (GPP), net photosynthesis (PSN) and normalized difference vegetation index (NDVI), with traditional age-based methods to improve stand volume estimation in Eucalyptus plantations. MODIS GPP was first evaluated against flux tower measurements, showing moderate agreement and systematic biases, particularly during periods of highest and lowest productivity in the first years after planting, with an RMSE of 19.65 gC m-2 8day-1 and R2 of 0.38. Multiple linear regression (MLR) and two machine learning models, including random forest (RF) and stochastic gradient boosting (SGB), were used to estimate stand volume by incorporating cumulative MODIS indices (Cgpp, Cpsn and Cndvi) and stand age. The SGB model showed the best performance using the full dataset, including stands aged from 1.6 to 8.4 years, with an RMSE of 22.63 m3 ha-1, an rRMSE of 17.15% and an R2 of 0.90. We showed that including cumulative indices from the first two years of growth significantly improved the model’s ability to predict growth dynamics in middle-aged to mature stands. These results highlight the utility of MODIS productivity products for medium to large-scale plantation management, providing scalable and cost-effective monitoring of stand volume.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1555887</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1555887</link>
        <title><![CDATA[BERT Bi-modal self-supervised learning for crop classification using Sentinel-2 and Planetscope]]></title>
        <pubdate>2025-05-01T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ankit Patnala</author><author>Martin G. Schultz</author><author>Juergen Gall</author>
        <description><![CDATA[Crop identification and monitoring of crop dynamics are essential for agricultural planning, environmental monitoring, and ensuring food security. Recent advancements in remote sensing technology and state-of-the-art machine learning have enabled large-scale automated crop classification. However, these methods rely on labeled training data, which requires skilled human annotators or extensive field campaigns, making the process expensive and time-consuming. Self-supervised learning techniques have demonstrated promising results in leveraging large unlabeled datasets across domains. Yet, self-supervised representation learning for crop classification from remote sensing time series remains under-explored due to challenges in curating suitable pretext tasks. While bimodal self-supervised approaches combining data from Sentinel-2 and Planetscope sensors have facilitated pre-training, existing methods primarily exploit the distinct spectral properties of these complementary data sources. In this work, we propose novel self-supervised pre-training strategies inspired from BERT that leverage both the spectral and temporal resolution of Sentinel-2 and Planetscope imagery. We carry out extensive experiments comparing our approach to existing baseline setups across nine test cases, in which our method outperforms the baselines in eight instances. This pre-training thus offers an effective representation of crops for tasks such as crop classification.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1574347</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1574347</link>
        <title><![CDATA[Positive correlation between the Po River discharge and ocean colour trends of Chl and TSM in the Adriatic Sea]]></title>
        <pubdate>2025-04-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Iacopo Vona</author><author>Simone Colella</author><author>Michela Sammartino</author><author>Vittorio E. Brando</author><author>Federico Falcini</author>
        <description><![CDATA[Coastal areas represent delicate and complex environments due to the interconnection between land and sea, where marine, fluvial and anthropogenic stressors combine threatening and undermining coastal health. Sea level rise and increasing storminess, for instance, lead to more frequent coastal flooding and habitat loss due to erosion; sediment supply by rivers, on the other hand, helps coastal areas to balance and restore habitat loss. However, excessive riverine nutrient inputs may lead to coastal eutrophication phenomena, putting coastal ecosystem as well as coastal communities at serious risk. Here, we compute high resolution (300 m) Chlorophyll-a (Chl) and Total Suspended Matter (TSM, a proxy for sediment concentration) trends over the Adriatic Sea by using the single sensors MERIS (from 2003 to 2012) and OLCI (from 2017–2024) data, to study the response of the marine ecosystem to human and/or environmental pressures, and thus for detecting coastal areas likely subject to eutrophication and/or sediment starvation. Such an analysis is complemented by Po River discharge data to investigate the role of river outputs in shaping the observed trends within the Adriatic basin. Our results reveal Chl and TSM trends in the northern part of the Adriatic basin being positively correlated with the Po River discharge during the investigated period, for both MERIS and OLCI data. Increases/decreases in the Po River outflow resulted in positive/negative Chl and TSM trends. Although a negative trend of Chl was documented within the Adriatic Sea in the last 25 years, Po River load fluctuations regulate long- and short-term, local trends of both Chl and TSM in the North Adriatic basin. This result suggests a direct relationship existing between river discharge and statistical trends of TSM and Chl in delta areas.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1544375</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1544375</link>
        <title><![CDATA[Spatiotemporal variability of chlorophyll-a concentration in the South Brazil Bight using 25 years of multi-sensor orbital data (1998–2022)]]></title>
        <pubdate>2025-03-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>João Felipe Cardoso dos Santos</author><author>Milton Kampel</author><author>Vincent Vantrepotte</author>
        <description><![CDATA[Chlorophyll-a (Chl-a) concentration is a key climate variable, as its variability is associated with meteorological and oceanographic processes. This study analyzed 25 years (1998–2022) of Chl-a data from the European Space Agency (ESA) Ocean Colour Climate Change Initiative (OC-CCI) multisensor archive for the South Brazil Bight, Southwestern Atlantic. Temporal variability and trends were assessed using the Census X11 method, Mann-Kendall, and Sens’ slope tests. The ESA OC-CCI data highlight reliable regional performance, although Chl-a concentrations above 10 mg.m−3 were underestimated. Temporal analyses showed the lowest Chl-a variability (29%) in open ocean waters, with 81% of the variability attributed to seasonal dynamics influenced by the South Atlantic Subtropical Gyre (SASG). A negative Chl-a trend of −11.0% was observed over the 25-year period, attributed to the expansion of the oligotrophic area of the SASG. In the shelf areas southwest of São Sebastião Island, Chl-a variability was moderate (34%–39%), with no discernible long-term trend, but significant interannual variability (44%). The Cape Frio upwelling region shows an increasing Chl-a trend (14.5% in the last 25 years), driven by atmospheric circulation affecting local winds. The highest Chl-a variability (74%) occurred along the southern continental shelf, associated with seasonal nutrient inputs from the Subtropical Shelf Front, with a Chla-a trend increase of 7.5% in 25 years. These results highlight the dynamic and variable Chl-a responses to environmental forcing across the South Brazil Bight.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2024.1483295</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2024.1483295</link>
        <title><![CDATA[Sentinel-1 (S1) time series alignment method for rapeseed fields mapping]]></title>
        <pubdate>2025-02-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Saeideh Maleki</author><author>Nicolas Baghdadi</author><author>Sami Najem</author><author>Cassio Fraga Dantas</author><author>Dino Ienco</author><author>Hassan Bazzi</author>
        <description><![CDATA[IntroductionThis paper presents a comprehensive analysis of rapeseed fields mapping using Sentinel-1 (S1) time series data. We applied a time series alignment method to enhance the accuracy of rapeseed fields detection, even in scenarios where reference label data are limited or not available.MethodsTo this end, for five different study sites in France and North America, we first investigated the temporal transferability of the classifiers across several years within the same site, specifically using the Random Forest (RF) and InceptionTime algorithms. We then examined the spatiotemporal transferability of the classifiers when a classifier trained on one site and year was used to generate rapeseed fields map for another site and year. Next, we proposed an S1 time series alignment method to improve classification accuracy across sites and years by accounting for temporal shifts caused by differences in agricultural practices and climatic conditions between sites.Results and discussionThe main results demonstrated that rapeseed detection for 1 year, using training data from another year within the same site, achieved high accuracy, with F1 scores ranging from 85.5% to 97% for RF and from 88.2% to 98.3% for InceptionTime. When classifying using one-year training data from one site to classify another year in a different site, F1 scores varied between 48.8% and 97.7% for both RF and InceptionTime. Using a three year training dataset from one site to classify rapeseed fields in another site resulted in F1 scores ranging from 82.7% to 97.8% with RF and from 88.7% to 97.1% with InceptionTime. The proposed alignment method, designed to enhance classification using training and test data from different sites, improved F1 scores by up to 46.7%. These findings confirm the feasibility of mapping rapeseed with S1 images across various sites and years, highlighting its potential for both national and international agricultural monitoring initiatives.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2025.1542181</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2025.1542181</link>
        <title><![CDATA[Past and future trends in swiss snow cover: multi-decades analysis using the snow observation from space algorithm]]></title>
        <pubdate>2025-02-13T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Charlotte Poussin</author><author>Pablo Timoner</author><author>Pascal Peduzzi</author><author>Gregory Giuliani</author>
        <description><![CDATA[Despite the large availability of satellite and in-situ data on snow cover in the Northern Hemisphere, long-term assessments at an adequate resolution to capture the complexities of mountainous terrains remain limited, particularly for countries like Switzerland. This study addresses this gap by employing two products—the monthly NDSI (Normalized Difference Snow Index) and snow cover products—derived from the Snow Observation from Space (SOfS) algorithm to monitor snow cover dynamics across Switzerland over the past 37 years. The pixel-wise analysis reveals significant negative trends in the monthly NDSI across all seasons, with the most pronounced decreases at low to mid-elevations, particularly in winter and spring (e.g., a 50% reduction in NDSI for pixels showing positive significative trends in winter below 1,000 m, and a 43% reduction in spring between 1,000 and 2,000 m). Similarly, snow cover area has declined significantly, with reductions of −13% to −15% in spring for the transitional zones between 1,000–1,500 m and 1,500–2,000 m. Furthermore, the monthly NDSI values are more strongly influenced by temperature than precipitation, especially at lower altitudes. To estimate trends in snow cover for the 21st century, we modelled the relationship between snow presence and two climatic variables (temperature and precipitation) using a binomial generalized linear mixed model (GLMM). In the context of climate change, projections under various greenhouse gas emission scenarios suggest further declines in snow cover by the end of the century. Even with moderate climate action (RCP 2.6), snow-free areas could expand by 22% at lower elevations by 2100. Under the more extreme scenario (RCP 8.5), snow-free regions could increase by over 43%, with significant impacts during the transitional months of April and May. The SOfS algorithm, developed within the Swiss Data Cube, provides valuable insights into snow cover dynamics across Switzerland. Complementing in-situ observations, this innovative approach is essential for assessing snow cover changes and guiding adaptation strategies in a country where snow is not only an environmental indicator but also a cultural and economic asset.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2024.1480101</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2024.1480101</link>
        <title><![CDATA[Bi-modal contrastive learning for crop classification using Sentinel-2 and Planetscope]]></title>
        <pubdate>2024-12-05T00:00:00Z</pubdate>
        <category>Methods</category>
        <author>Ankit Patnala</author><author>Scarlet Stadtler</author><author>Martin G. Schultz</author><author>Juergen Gall</author>
        <description><![CDATA[Remote sensing has enabled large-scale crop classification for understanding agricultural ecosystems and estimating production yields. In recent years, machine learning has become increasingly relevant for automated crop classification. However, the existing algorithms require a huge amount of annotated data. Self-supervised learning, which enables training on unlabeled data, has great potential to overcome the problem of annotation. Contrastive learning, a self-supervised approach based on instance discrimination, has shown promising results in the field of natural as well as remote sensing images. Crop data often consists of field parcels or sets of pixels from small spatial regions. Additionally, one needs to account for temporal patterns to correctly label crops. Hence, the standard approaches for landcover classification cannot be applied. In this work, we propose two contrastive self-supervised learning approaches to obtain a pre-trained model for crop classification without the need for labeled data. First, we adopt the uni-modal contrastive method (SCARF) and, second, we use a bi-modal approach based on Sentinel-2 and Planetscope data instead of standard transformations developed for natural images to accommodate the spectral characteristics of crop pixels. Evaluation in three regions of Germany and France shows that crop classification with the pre-trained multi-modal model is superior to the pre-trained uni-modal method as well as the supervised baseline models in the majority of test cases.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2024.1492534</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2024.1492534</link>
        <title><![CDATA[Evaluating the applicability of landsat 8 data for global time series analysis]]></title>
        <pubdate>2024-11-08T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ehsan Rahimi</author><author>Chuleui Jung</author>
        <description><![CDATA[IntroductionFactors such as (1) the number of satellite images available for a specific study and (2), the applicability of these images in terms of cloud cover, can reduce the overall accuracy of time series studies from earth observation. In this context, the Landsat 8 dataset stands out as one of the most widely used and versatile datasets for time series analysis, building on the strengths of its predecessors with its advanced features. However, despite these enhancements, there is a significant gap in the literature regarding a comprehensive assessment of Landsat 8’s performance. Specifically, there is a need for a detailed evaluation of image availability and cloud cover percentages across various global paths and rows.MethodsTo address this gap, we utilized the Landsat 8 Collection 2 dataset available through Google Earth Engine (GEE). Our approach involved filtering the dataset to focus on Landsat 8 images captured between 2014 and 2023 across all paths and rows. Using the Earth Engine Python API, we accessed and processed this data, extracting key information such as the number of available images and their associated cloud cover percentages.Results and DiscussionOur analysis of Landsat 8 image availability revealed that regions such as Australia, parts of Africa, the Middle East, Western Asia, and Southern North America benefit from a higher frequency of Landsat imagery, while Northern Asia and Northern North America have fewer images available. Latitude-specific trends show that areas between 55 and 82 degrees receive notably fewer images. We also found that regions like central Australia, northern Africa, and the Middle East generally experience lower cloud cover, while central Africa, and northern parts of Asia, Europe, and North America have higher cloudiness. Latitudinal trends show a significant drop in cloud cover from approximately 90% at latitudes -60 to -20 degrees to below 10%, with a rise near the Equator. Cloud cover decreases again from 0 to 20 degrees latitude but increases between 20 and 60 degrees. Europe has the highest average cloud cover at 42.5%, impacting image clarity, whereas Africa has the lowest average at 23.3%, indicating clearer satellite imagery.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2024.1280712</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2024.1280712</link>
        <title><![CDATA[Detecting groundwater dependence and woody vegetation restoration with NDVI and moisture trend analyses in an Indonesian karst savanna]]></title>
        <pubdate>2024-08-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Penelope Godwin</author><author>Siyuan Tian</author><author>Clément Duvert</author><author>Penny Wurm</author><author>Norman Riwu Kaho</author><author>Andrew Edwards</author>
        <description><![CDATA[Woody vegetation restoration projects are an important feature of landscape function in Indonesian karst savannas. Understanding the relationship between available moisture and vegetation condition can assist with the planning and implementation of revegetation efforts. Working at vegetation restoration sites in East Nusa Tenggara, Indonesia, we applied a windowed cross-correlation method to mean values of NDVI to examine the lag between moisture input and NDVI response for both rainfall and soil moisture between 1999 and 2018. To test for increasing or decreasing trends in NDVI and rainfall time series, we undertook Mann–Kendall trend analyses. We identified increasing trends in Landsat 7 NDVI at two of four restoration sites, with annual increases in NDVI of 2.7 and 3.74 × 10−4 respectively. We found that rainfall dependent sites had significant Pearson’s correlations with NDVI ranging from 0.52 to 0.71, while NDVI was not correlated with rainfall at shallow groundwater sites. There was a clear negative effect of the very dry period on all sites, and this was less pronounced at shallow groundwater sites. Wet years resulted in a positive response to NDVI across all sites, while the response was lower in very wet years with annual rainfall above 1,200 mm. We found that between 2 and 4 months of antecedent rainfall gave the highest correlation with NDVI, while for soil moisture the closest relationship was found with no lag and 1 month lag. Through this study, we demonstrated the applicability of using NDVI, rainfall, and soil moisture trend analyses to identify groundwater-dependent vegetation patches and monitor the effectiveness of vegetation restoration.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2024.1042624</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2024.1042624</link>
        <title><![CDATA[Perspectives on modifiable spatiotemporal unit problems in remote sensing of agriculture: evaluating rice production in Vietnam and tools for analysis]]></title>
        <pubdate>2024-06-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Brad G. Peter</author><author>Joseph P. Messina</author><author>Victoria Breeze</author><author>Cadi Y. Fung</author><author>Abhinav Kapoor</author><author>Peilei Fan</author>
        <description><![CDATA[Measuring agricultural productivity is a multiscale spatiotemporal problem that requires multiscale solutions. In Vietnam, rice comprises a substantial portion of the cultivated area and is a major export crop that supplies much of the global food system. Understanding the when and where of rice productivity is vital to addressing changes to yields and food security, yet descriptive summarizations will vary depending on the spatial or temporal scale of analysis. This paper explores rice trends across Vietnam over a 19-year period, giving specific attention to modifiable spatiotemporal unit problems by evaluating productivity across multiple time periods and administrative levels. A generalizable procedure and tools are offered for visualizing multiscale time-series remote sensing data in matrix and map form, not only to elucidate the effects of modifiable spatiotemporal unit problems, but also to demonstrate how these problems serve as a useful research framework. Remote sensing indices (e.g., LAI and EVI) were evaluated against national and provincial estimates across Vietnam during multiple crop production periods using the Pearson Correlation Coefficient (PCC) to establish a relationship. To overcome challenges posed by long-term observations masking emerging phenomena, time-series matrices and multi-spatial and multi-temporal maps were produced to show when, where, and how rice productivity across Vietnam is changing. Results showed that LAI and EVI are favorable indices for measuring rice agriculture in Vietnam. At the province scale, LAI compared to nationally reported production estimates reached a Pearson’s r of 0.960; 0.974 for EVI during the spring crop production period. For questions such as, “What portion of Vietnam exhibits a negative linear trend in rice production?”, the answer depends on how space and time are organized. At the province scale, 25.4% of Vietnam can be observed as exhibiting a negative linear trend; however, when viewed at the district scale, this metric rises to 45.7%. This research contributes to the discussion surrounding ontological problems of how agricultural productivity is measured and conveyed. To better confront how agriculture is assessed, adopting a multiscale framework can provide a more holistic view than the conventional single spatial or temporal selection.]]></description>
      </item>
      </channel>
    </rss>