High-resolution Time Series Research Articles

Similarities and differences in the gene expression signatures of physiological age versus future lifespan.

Across all taxa of life, individuals within a species exhibit variable lifespans. Differences in genotype or environment are not sufficient to explain this variance, as even isogenic Caenorhabditis elegans nematodes reared under uniform conditions show significant variability in lifespan. To investigate this phenomenon, we used lifespan-predictive biomarkers to isolate, at mid-adulthood, prospectively long- and short-lived individuals from an otherwise identical population. We selected two biomarkers which correlated positively with lifespan, lin-4p::GFP and mir-243p::GFP, and two which correlated negatively, mir-240/786p::GFP and autofluorescence. The gene-expression signature of long versus short future lifespan was strikingly similar across all four biomarkers tested. Since these biomarkers are expressed in different tissues, these results suggest a shared connection to a global health state correlated with future lifespan. To further investigate this underlying state, we compared the transcriptional signature of long versus short future lifespan to that of chronologically young versus old individuals. By comparison to a high-resolution time series of the average aging transcriptome, we determined that subpopulations predicted to be long- or short-lived by biomarker expression had significantly different transcriptional ages despite their shared chronological age. We found that this difference in apparent transcriptional age accounted for the majority of differentially expressed genes associated with future lifespan. Interestingly, we also identified several genes whose expression consistently separated samples by biomarker expression independent of apparent transcriptional age. These results suggest that the commonalities in the long-lived versus short-lived state reported across different biomarkers of aging extends beyond simply transcriptionally young versus transcriptionally old.

The overflowing atmosphere of WASP-121 b. High-resolution transmission spectroscopy with VLT/CRIRES+

Transmission spectroscopy is a prime method to study the atmospheres of extrasolar planets. We obtained a high-resolution spectral transit time series of the hot Jupiter with CRIRES$^+$ to study its atmosphere via transmission spectroscopy of the triplet lines. Our analysis shows a prominent absorption feature moving along with the planetary orbital motion, which shows an observed, transit-averaged equivalent width of approximately 30\,m a slight redshift, and a depth of about 2\,<!PCT!>, which can only be explained by an atmosphere overflowing its Roche lobe. We carried out 3D hydrodynamic modeling to reproduce the observations, which favors asymmetric mass loss with a more pronounced leading tidal tail, possibly also explaining observational evidence for additional absorption stationary in the stellar rest frame. A trailing tail is not detectable. From our modeling, we derived estimates of $ for the stellar and $5.4 for the planetary mass loss rate, which is consistent with X-ray and extreme-ultraviolet (XUV) driven mass loss in

Mid-Pleistocene aridity and landscape shifts promoted Palearctic hominin dispersals

Population expansions and contractions out of and into Africa since the early Pleistocene have influenced the course of human evolution. While local- and regional-scale investigations have provided insights into the drivers of Eurasian hominin dispersals, a continental-scale and integrated study of hominin-environmental interactions across Palearctic Eurasia has been lacking. Here, we report high-resolution (up to ∼5-10 kyr sample interval) carbon isotope time series of loess deposits in Central Asia and northwest China, a region dominated by westerly winds, providing unique paleoecological and paleoclimatic records for over ~3.6 Ma. These data, combined with further syntheses of Pleistocene paleontological and archaeological records and spatio-temporal distributions of Eurasian eolian deposits and river terraces, demonstrate a pronounced transformation of landscapes around the Mid-Pleistocene Climate Transition. Increased climate amplitude and aridity fluctuations over this period led to the widespread formation of more open habitats, river terraces, and desert-loess landscapes, pushing hominins to range more widely and find solutions to increasingly challenging environments. Mid-Pleistocene climatic and ecological transitions, and the formation of modern desert and loess landscapes and river networks, emerge as critical events during the dispersal of early hominins in Palearctic Eurasia.

Abstract 4129709: Aspirin-Nanoparticle for Dual Therapies: Targeted Anti-Inflammatory and Prolonged Anti-Platelet Effects for Atherosclerosis

Background: The current unmet needs for aspirin usage in atherosclerosis lie in its short half-life and narrow indication for anti-platelet effects. Daily aspirin intake is mandatory, and the anti-inflammatory effects of aspirin for atherosclerosis have not successfully translated to clinical practice. Nanoparticles remain in circulation for 2-3 days, with a large portion being cleared by splenic monocytes, which are known to inherently target inflamed sites. Hypothesis: By altering the pharmacokinetics of aspirin through loading into nanoparticles, aspirin-nanoparticles can exert prolonged anti-platelet effects and target atherosclerosis sites via monocyte carriers for anti-inflammatory effects, resulting in dual therapies. Methods: Splenic monocytes were loaded with aspirin-liposomes and co-cultured with endothelial cells or platelets to examine the interactions between them using high-resolution time-series microscopy. Prolonged anti-platelet effects and targeted anti-inflammatory effects of aspirin were validated in intact mice and hindlimb ischemia models, respectively. Furthermore, the dual therapies of aspirin-liposomes were validated in an atherosclerotic mouse model created by partial carotid ligation and a western diet in apoE gene knock-out mice. Results: When splenic monocytes were loaded with aspirin-liposomes, they emitted extracellular vesicles (EVs) loaded with aspirin towards endothelial cells or platelets. As inflamed cells upregulate caveolin expression, they uptake an increased amount of transferred EVs compared to non-inflamed cells. Additionally, aspirin-liposomes showed prolonged circulation time and increased splenic accumulation compared to aspirin itself, resulting in prolonged anti-platelet effects (>7 days) and targeted anti-inflammatory effects at inflamed sites. Compared to the daily oral aspirin group in the atherosclerosis model, the weekly intravenous aspirin-liposome group showed superior therapeutic effects, including attenuated systemic and local inflammation and patent lumen in atherosclerotic sites. Conclusion: Aspirin-nanoparticles can exert prolonged anti-platelet effects combined with targeted anti-inflammatory effects, resulting in superior therapeutic effects on atherosclerosis.

The impact of data resolution on dynamic causal inference in multiscale ecological networks.

While it is commonly accepted that ecosystem dynamics are nonlinear, what is often not acknowledged is that nonlinearity implies scale-dependence. With the increasing availability of high-resolution ecological time series, there is a growing need to understand how scale and resolution in the data affect the construction and interpretation of causal networks-specifically, networks mapping how changes in one variable drive changes in others as part of a shared dynamic system ("dynamic causation"). We use Convergent Cross Mapping (CCM), a method specifically designed to measure dynamic causation, to study the effects of varying temporal and taxonomic/functional resolution in data when constructing ecological causal networks. As the system is viewed at different scales relationships will appear and disappear. The relationship between data resolution and interaction presence is not random: the temporal scale at which a relationship is uncovered identifies a biologically relevant scale that drives changes in population abundance. Further, causal relationships between taxonomic aggregates (low-resolution) are shown to be influenced by the number of interactions between their component species (high-resolution). Because no single level of resolution captures all the causal links in a system, a more complete understanding requires multiple levels when constructing causal networks.

A minute-resolution downscaling algorithm for high-resolution global irradiance time series

Numerous studies have demonstrated the significant impact of the resolution of solar irradiation data on the outcomes of hourly production models. Accurate integration of photovoltaic (PV) systems sometimes demands a high-resolution global horizontal irradiance (GHI) time series to capture the rapid fluctuations in PV power output induced by swift irradiance changes. Most of the available databases provide data at hourly resolution, leading to a lack of accuracy in PV simulations. Those existing hourly averages of global horizontal irradiance in open sources fail to represent this volatility adequately, especially when PV systems are coupled with fast ramp rate technologies. In the present work, an easy-to-use algorithm is implemented to synthesize high-resolution GHI time series from hourly averaged and clear sky irradiance datasets. By employing Linear interpolation, a technique that helps to achieve the desired time resolution and afterward computing critical factors, the algorithm identifies periods characterized by short-term weather phenomena, thus creating a high-resolution time series that accurately represents these dynamics. Avoiding the probabilistic components and machine learning techniques conserves computational power and reduces calculation time, but this comes at the cost of reduced fidelity in reproducing the results. Improving accuracy in PV simulations is not always directly related to reproducing real phenomena, but enhancing the amount of information contained in the data is sufficient. This study’s approach enhances user-friendliness and facilitates seamless integration into existing energy modeling frameworks, aiming for representation with sub-hourly time steps. The algorithm’s effectiveness is demonstrated by applying the model to hourly averaged data to revert them to a one-minute time step, and finally comparing the synthetically produced one-minute GHI data to the original measured data. The comparative analysis between synthesized and measured data demonstrated a strong agreement, with normalized mean bias error (MBE) values ranging between 1.8% and 9.6% and normalized root mean square error (NRMSE) values between 2.7% and 16.1%, depending on weather conditions. Additionally, the coefficient of determination (R2) consistently remained above 0.64. Successful algorithm validation makes our algorithm suitable for use in meteorological datasets and locations, with similar climatic characteristics.

Long-term investigation on the daily variability of microplastic concentration and composition - Monitoring in the effluent of a wastewater treatment plant

The discharge of treated wastewater into receiving waters by wastewater treatment plants (WWTPs) is considered as one of the main pathways for microplastics (MPs) to enter the environment. To gain a better understanding of the temporal variability of MPs in WWTP effluents, this study investigated the concentration and composition (size, shape and polymer type) of MPs in the effluent of a German WWTP over the course of one month. 24-hour mixed samples were collected daily by a custom built automated sampling unit for MPs. Particles and fibers ≥11 μm were analyzed using Fourier transform infrared microspectroscopy. The MP concentration showed large daily fluctuations and ranged between 9.64 103 m−3 and 8.44 104 m−3 MPs over the study period. However, there was no significant correlation between the MP concentration and the precipitation or discharge from the WWTP. In contrast to the MP concentration, the MP composition in terms of size and shape was consistent over the study period. There were strong correlations between the time series of the polymer types polypropylene, polyethylene, polystyrene, polyester, ethylene-vinyl-acetate, cellulose artificially modified as well as the polymer cluster acrylates/polyurethanes/varnish. The time series of polyamide showed no significant correlation with the time series of any other polymer type. This study established a one month long high-resolution time series of MP concentration and composition, and thus provides a valuable basis for future research on the temporal variability of MP inputs into the environment from WWTP effluents.

Single-cell stimulus-response gene expression trajectories reveal the stimulus specificities of dynamic responses by single macrophages

Macrophages induce the expression of hundreds of genes in response to immune threats. However, current technology limits our ability to capture single-cell inducible gene expression dynamics. Here, we generated high-resolution time series single-cell RNA sequencing (scRNA-seq) data from mouse macrophages responding to six stimuli, and imputed ensembles of real-time single-cell gene expression trajectories (scGETs). We found that dynamic information contained in scGETs substantially contributes to macrophage stimulus-response specificity (SRS). Dynamic information also identified correlations between immune response genes, indicating biological coordination. Furthermore, we showed that the microenvironmental context of polarizing cytokines profoundly affects scGETs, such that measuring response dynamics offered clearer discrimination of the polarization state of individual macrophage cells than single time-point measurements. Our findings highlight the important contribution of dynamic information contained in the single-cell expression responses of immune genes in characterizing the SRS and functional states of macrophages.

Gated recurrent units for modelling time series of soil temperature and moisture: An assessment of performance and process reflectivity

Soil temperature and moisture are important variables controlling ecological processes, but continuous high-resolution data are rarely available. Therefore, we used the correlation with widely accessible meteorological variables, including air temperature and precipitation, to develop models that predict time series of soil temperature and moisture. To model high-resolution time series, predictor and target variables had a temporal resolution of 1 h. We tested the applicability of Gated Recurrent Units with time series from one exemplary site. The models showed a high predictability on the four years test set with a mean absolute error of 0.87°C for soil temperature and 3.20% volumetric water content for soil moisture. We further investigated the plausibility of the models by passing simplified synthetic data to the trained models and thereby proved their ability to reflect known processes. Finally, we showed the potential to apply the models to other sites and soil depths using transfer learning.

Innovations through crop switching happen on the diverse margins of US agriculture

Crop switching, in which farmers grow a crop that is novel to a given field, can help agricultural systems adapt to changing environmental, cultural, and market forces. Yet while regional crop production trends receive significant attention, relatively little is known about the local-scale crop switching that underlies these macrotrends. We characterized local crop-switching patterns across the United States using the US Department of Agriculture (USDA) Cropland Data Layer, an annual time series of high resolution (30 m pixel size) remote-sensed cropland data from 2008 to 2022. We found that at multiple spatial scales, crop switching was most common in sparsely cultivated landscapes and in landscapes with high crop diversity, whereas it was low in homogeneous, highly agricultural areas such as the Midwestern corn belt, suggesting a number of potential social and economic mechanisms influencing farmers' crop choices. Crop-switching rates were high overall, occurring on more than 6% of all US cropland in the average year. Applying a framework that classified crop switches based on their temporal novelty (crop introduction versus discontinuation), spatial novelty (locally divergent versus convergent switching), and categorical novelty (transformative versus incremental switching), we found distinct spatial patterns for these three novelty dimensions, indicating a dynamic and multifaceted set of cropping changes across US farms. Collectively, these results suggest that innovation through crop switching is playing out very differently in various parts of the country, with potentially significant implications for the resilience of agricultural systems to changes in climate and other systemic trends.

High-resolution time-series classification in smart manufacturing systems

High-resolution time-series data is increasingly prevalent in today’s smart manufacturing systems driven by the proliferation of sensors and data acquisition technologies. However, classification tasks on such data face challenges like collinearity, model instability, poor generalization, and overfitting. This paper investigates techniques capable of handling high-resolution time-series classification (TSC) tasks in the manufacturing domain. High-resolution time-series data presents challenges impacting the concepts essential for classification algorithms. Additionally, increased noise and the extensive feature space further complicate classification performance, emphasizing the need for innovative solutions to process this data efficiently on resource-constrained devices. In this paper, we address this research gap by defining the problem in depth, investigating possible solutions, and evaluating a subset of solutions in a manufacturing case study. We utilize a CNC machining dataset with over 100,000 data points per time-series. We examine algorithms representing two main approaches: feature engineering for data transformation and dimensionality reduction, and advanced machine learning and deep learning models to capture long-term dependencies. Specifically, we implement Discrete Fourier Transform, Symbolic Aggregate Approximation, Symbolic Fourier Approximation, ARSENAL, DrCIF, and ResNet algorithms for TSC. Experimental results highlight the trade-off between accuracy and computational expense. While ARSENAL and DrCIF achieve high accuracy, their runtimes are notably high. Feature engineering methods offer competitive accuracy with very low runtimes, and ResNet strikes a compelling balance by surpassing benchmarks in accuracy while maintaining reasonable computational costs. These findings can aid in adopting appropriate tools to successfully harness manufacturing big data to derive actionable insights for process improvements and optimization. The novelty of this research lies in addressing the specific challenges of classification tasks on high-resolution time-series data within the manufacturing domain, exploring diverse techniques, applying them to a case study, and providing a nuanced analysis of algorithmic performance with practical implications.

Multivariate characterisation of a blackberry–alder agroforestry system in South Africa: hydrological, pedological, dendrological and meteorological measurements

Abstract. Trees established in linear formations can be utilised as windbreak structures on farms as a form of agroforestry system. We present an extensive data package collected from an active berry farm located near Stellenbosch, South Africa, considering hydrological, pedological, dendrological and meteorological measurements centred around an Italian alder (Alnus cordata (Loisel.) Duby) windbreak and a blackberry (Rubus fruticosus L. Var. “Waldo”) crop. Data were collected between September 2019 and June 2021. The data are available from Hassler et al. (2024) and include the following measurements (i) meteorological variables – solar radiation, precipitation characteristics, vapour pressure deficit, air temperature, humidity, atmospheric pressure, wind speed and direction, gust speed, and lightning strikes and distance recorded at 10 min intervals; (ii) hydrological measurements – soil moisture and matric potential in two profiles at 15 min intervals alongside soil samples at various depths describing soil texture, hydraulic conductivity, and water retention parameters; (iii) soil characteristics – a soil profile description accompanied by 60 topsoil samples describing carbon, nitrogen, and exchangeable base cation concentrations, as well as potential cation exchange capacity and descriptions of soil texture; and (iv) dendrological measurements – point cloud data for the studied windbreak trees and surrounding features, cylinder models of the windbreak trees with volume and biomass data, and foliage data as a product of an existing leaf creation algorithm. The described dataset provides a multidisciplinary approach to assess the impact and interaction of windbreaks and tree structures in agroforestry landscapes, aiding future work concerning water fluxes, nutrient distribution, microclimate and carbon sequestration. The dataset, including high-resolution time series and point cloud data, offers valuable insights for managing the windbreak's influence and serves as a unique training dataset for spatial analysis (https://doi.org/10.5880/fidgeo.2023.028, Hassler et al., 2024).

Single-plant-omics reveals the cascade of transcriptional changes during the vegetative-to-reproductive transition.

Plants undergo rapid developmental transitions, which occur contemporaneously with gradual changes in physiology. Moreover, individual plants within a population undergo developmental transitions asynchronously. Single-plant-omics has the potential to distinguish between transcriptional events that are associated with these binary and continuous processes. Furthermore, we can use single-plant-omics to order individual plants by their intrinsic biological age, providing a high-resolution transcriptional time series. We performed RNA-seq on leaves from a large population of wild-type Arabidopsis (Arabidopsis thaliana) during the vegetative-to-reproductive transition. Though most transcripts were differentially expressed between bolted and unbolted plants, some regulators were more closely associated with leaf size and biomass. Using a pseudotime inference algorithm, we determined that some senescence-associated processes, such as the reduction in ribosome biogenesis, were evident in the transcriptome before a bolt was visible. Even in this near-isogenic population, some variants are associated with developmental traits. These results support the use of single-plant-omics to uncover rapid transcriptional dynamics by exploiting developmental asynchrony.

Monitoring resilience in bursts

The possibility to anticipate critical transitions through detecting loss of resilience has attracted attention in many fields. Resilience indicators rely on the mathematical concept of critical slowing down, which means that a system recovers more slowly from external perturbations when it gets closer to tipping point. This decrease in recovery rate can be reflected in rising autocorrelation and variance in data. To test whether resilience is changing, resilience indicators are often calculated using a moving window in long, continuous time series of the system. However, for some systems, it may be more feasible to collect several high-resolution time series in short periods of time, i.e., in bursts. Resilience indicators can then be calculated to detect a change of resilience between such bursts. Here, we compare the performance of both methods using simulated data and showcase the possible use of bursts in a case study using mood data to anticipate depression in a patient. With the same number of data points, the burst approach outperformed the moving window method, suggesting that it is possible to downsample the continuous time series and still signal an upcoming transition. We suggest guidelines to design an optimal sampling strategy. Our results imply that using bursts of data instead of continuous time series may improve the capacity to detect changes in resilience. This method is promising for a variety of fields, such as human health, epidemiology, or ecology, where continuous monitoring can be costly or unfeasible.

Unpacking satellite pixels: UAVs reveal fine-scale drivers of land surface phenology in a winter rainfall shrubland

Land surface phenology (LSP) can reveal important connections between vegetation dynamics and climate but remains poorly understood in evergreen winter-rainfall shrublands globally. Field-based studies have indicated diverse plant functional strategies in shrublands, but further work is required to link LSP to vegetation functional composition in these regions. We analysed time-series of the normalised difference vegetation index (NDVI) in fynbos shrublands of South Africa using multi-spectral imagery from satellites and unmanned aerial vehicles (UAVs). We investigated the climate drivers of seasonal vegetative phenology and long-term NDVI trends at multiple spatial scales ranging from the landscape to individual species. At coarse spatial resolutions, NDVI time-series indicated rainfall-driven vegetation dynamics in fynbos, both at inter and intra-annual time scales. However, high-resolution time-series from UAVs exposed an underlying divergence in vegetative phenology and long-term NDVI trends between shallow and deep-rooted growth forms. Phenophases and NDVI trends of isolated, deep-rooted, overstory shrubs were decoupled from rainfall relative to dense overstory patches and shallow-rooted understory growth forms. Variations in growth form phenology were not detected at coarse spatial scales due to scaling and competitive effects based on the functional composition of the vegetation.

A dual RNA-seq analyses revealed dynamic arms race during the invasion of walnut by Colletotrichum gloeosporioides

BackgroundWalnut anthracnose caused by Colletotrichum gloeosporioides seriously endangers the yield and quality of walnut, and has now become a catastrophic disease in the walnut industry. Therefore, understanding both pathogen invasion mechanisms and host response processes is crucial to defense against C. gloeosporioides infection.ResultsHere, we investigated the mechanisms of interaction between walnut fruits (anthracnose-resistant F26 fruit bracts and anthracnose-susceptible F423 fruit bracts) and C. gloeosporioides at three infection time points (24hpi, 48hpi, and 72hpi) using a high-resolution time series dual transcriptomic analysis, characterizing the arms race between walnut and C. gloeosporioides. A total of 20,780 and 6670 differentially expressed genes (DEGs) were identified in walnut and C. gloeosporioides against 24hpi, respectively. Generous DEGs in walnut exhibited opposite expression patterns between F26 and F423, which indicated that different resistant materials exhibited different transcriptional responses to C. gloeosporioides during the infection process. KEGG functional enrichment analysis indicated that F26 displayed a broader response to C. gloeosporioides than F423. Meanwhile, the functional analysis of the C. gloeosporioides transcriptome was conducted and found that PHI, SignalP, CAZy, TCDB genes, the Fungal Zn (2)-Cys (6) binuclear cluster domain (PF00172.19) and the Cytochrome P450 (PF00067.23) were largely prominent in F26 fruit. These results suggested that C. gloeosporioides secreted some type of effector proteins in walnut fruit and appeared a different behavior based on the developmental stage of the walnut.ConclusionsOur present results shed light on the arms race process by which C. gloeosporioides attacked host and walnut against pathogen infection, laying the foundation for the green prevention of walnut anthracnose.

Warming effect of the desert regulates spatio-temporal distribution of cotton Verticillium wilt for the oasis agriculture ecosystem

Verticillium wilt (VW) is threatening global cotton yield and quality. However, the accurate spatio-temporal dynamics of cotton VW in large regions remain unclear, especially in the complicated oasis agriculture ecosystem. We explored the spatio-temporal distribution of VW in the cotton-dominated region of Northern Xinjiang characterized by a typical desert-oasis irrigation agriculture ecosystem, utilizing reconstructed high-resolution time series remote sensing data from 2019 to 2021. Results revealed that the area of VW-infected cotton remained consistently around 20 % each year. However, there were significant seasonal variations, with outbreaks peaking in August. Regarding the spatial pattern of cotton VW, the mean temperature (TMP) difference in irrigated cotton fields along the Gurbantunggut Desert-oasis gradient reaches a maximum of approximately 1 ℃ caused by warming effect of the desert on the oasis (WEDO) during the cotton growing period. This TMP difference drives the spatial pattern of cotton VW incidence characterized by a low-to-high-to-moderate trend. WEDO significantly suppresses the cotton VW incidence due to relatively higher TMP, forming the low-risk zone for cotton VW within 16 km near the Gurbantunggut Desert. Our study significantly enhances the understanding of the spatio-temporal dynamics of cotton VW in the distinctive oasis irrigation agricultural ecosystem and advances the accurate monitoring and assessment of cotton VW across large regions.

HD 110067 c has an aligned orbit

Planetary systems in mean motion resonances hold a special place among the planetary population. They allow us to study planet formation in great detail as dissipative processes are thought to have played an important role in their existence. Additionally, planetary masses in bright resonant systems can be independently measured via both radial velocities and transit timing variations. In principle, they also allow us to quickly determine the inclination of all planets in the system since, for the system to be stable, they are likely all in coplanar orbits. To describe the full dynamical state of the system, we also need the stellar obliquity, which provides the orbital alignment of a planet with respect to the spin of its host star and can be measured thanks to the Rossiter–McLaughlin effect. It was recently discovered that HD 110067 harbors a system of six sub-Neptunes in resonant chain orbits. We here analyze an ESPRESSO high-resolution spectroscopic time series of HD 110067 during the transit of planet c. We find the orbit of HD 110067 c to be well aligned, with a sky-projected obliquity of λ =6+24-26 deg. This result indicates that the current architecture of the system was reached through convergent migration without any major disruptive events. Finally, we report transit-timing variation in this system as we find a significant offset of 19 ± 4 min in the center of the transit compared to the published ephemeris.

Forecasting water resources from satellite image time series using a graph-based learning strategy

Abstract. In the context of climate change, it is important to monitor the dynamics of the Earth’s surface in order to prevent extreme weather phenomena such as floods and droughts. To this end, global meteorological forecasting is constantly being improved, with a recent breakthrough in deep learning methods. In this paper, we propose to adapt a recent weather forecasting architecture, called GraphCast, to a water resources forecasting task using high-resolution satellite image time series (SITS). Based on an intermediate mesh, the data geometry used within the network is adapted to match high spatial resolution data acquired in two-dimensional space. In particular, we introduce a predefined irregular mesh based on a segmentation map to guide the network’s predictions and bring more detail to specific areas. We conduct experiments to forecast water resources index two months ahead on lakes and rivers in Italy and Spain. We demonstrate that our adaptation of GraphCast outperforms the existing frameworks designed for SITS analysis. It also showed stable results for the main hyperparameter, i.e., the number of superpixels. We conclude that adapting global meteorological forecasting methods to SITS settings can be beneficial for high spatial resolution predictions.

Generating high-resolution hyperspectral time series datasets based on unsupervised spatial-temporal-spectral fusion network incorporating a deep prior

Over the past decade, image fusion has emerged as an indispensable tool for surface monitoring due to its capability to reconstruct high-quality surface reflectance. While satisfactory progress has been made in the spatial-spectral and spatial-temporal fusion of remote sensing images, the fusion of spatial-temporal-spectral data remains a challenging task. This challenge arises from the presence of multiple nonlinear relationships caused by inconsistent temporal, spatial, and spectral resolutions. In this paper, we propose a novel approach to address the spatial-temporal-spectral fusion of remote sensing images using a triple discriminator Generative Adversarial Network called TDGAN. Our approach represents the first attempt at spatial-temporal-spectral fusion based on deep learning techniques. Specifically, TDGAN achieves unsupervised learning by incorporating a deep spectral transformation prior, explores the application performance of the Swin Transformer in spectral super-resolution for the first time. Additionally, three discriminators are designed based on the prior consistencies: phenological consistency for data acquired at different times and spatial-spectral consistency for data acquired at the same time. These discriminators effectively enhance the prediction accuracy of missing hyperspectral images. Extensive simulations and real experiments were conducted to evaluate the effectiveness of our proposed TDGAN. The results demonstrate its robustness and comparable performance to other state-of-the-art methods. The proposed approach provides high-quality hyperspectral datasets with high spatial and temporal resolutions, facilitating continuous land cover observations.