Decomposing predictability to identify dominant causal drivers in complex ecosystems.

Ecosystems are complex systems of various physical, biological, and chemical processes. Since ecosystem dynamics are composed of a mixture of different levels of stochasticity and nonlinearity, handling these data is a challenge for existing methods of time series-based causal inferences. Here, we show that, by harnessing contemporary machine learning approaches, the concept of Granger causality can be effectively extended to the analysis of complex ecosystem time series and bridge the gap between dynamical and statistical approaches. The central idea is to use an ensemble of fast and highly predictive artificial neural networks to select a minimal set of variables that maximizes the prediction of a given variable. It enables decomposition of the relationship among variables through quantifying the contribution of an individual variable to the overall predictive performance. We show how our approach, EcohNet, can improve interaction network inference for a mesocosm experiment and simulated ecosystems. The application of the method to a long-term lake monitoring dataset yielded interpretable results on the drivers causing cyanobacteria blooms, which is a serious threat to ecological integrity and ecosystem services. Since performance of EcohNet is enhanced by its predictive capabilities, it also provides an optimized forecasting of overall components in ecosystems. EcohNet could be used to analyze complex and hybrid multivariate time series in many scientific areas not limited to ecosystems.

Confronting Deep-Learning and Biodiversity Challenges for Automatic Video-Monitoring of Marine Ecosystems.

With the availability of low-cost and efficient digital cameras, ecologists can now survey the world's biodiversity through image sensors, especially in the previously rather inaccessible marine realm. However, the data rapidly accumulates, and ecologists face a data processing bottleneck. While computer vision has long been used as a tool to speed up image processing, it is only since the breakthrough of deep learning (DL) algorithms that the revolution in the automatic assessment of biodiversity by video recording can be considered. However, current applications of DL models to biodiversity monitoring do not consider some universal rules of biodiversity, especially rules on the distribution of species abundance, species rarity and ecosystem openness. Yet, these rules imply three issues for deep learning applications: the imbalance of long-tail datasets biases the training of DL models; scarce data greatly lessens the performances of DL models for classes with few data. Finally, the open-world issue implies that objects that are absent from the training dataset are incorrectly classified in the application dataset. Promising solutions to these issues are discussed, including data augmentation, data generation, cross-entropy modification, few-shot learning and open set recognition. At a time when biodiversity faces the immense challenges of climate change and the Anthropocene defaunation, stronger collaboration between computer scientists and ecologists is urgently needed to unlock the automatic monitoring of biodiversity.

In Situ Measurements of Plankton Biorhythms Using Submersible Holographic Camera.

The paper presents a diagnostic complex for plankton studies using the miniDHC (digital holographic camera). Its capabilities to study the rhythmic processes in plankton ecosystems were demonstrated using the natural testing in Lake Baikal in summer. The results of in situ measurements of plankton to detect the synchronization of collective biological rhythms with medium parameters are presented and interpreted. The most significant rhythms in terms of the correlation of their parameters with medium factors are identified. The study shows that the correlation with water temperature at the mooring site has the greatest significance and reliability. The results are verified with biodiversity data obtained by the traditional mesh method. The experience and results of the study can be used for the construction of a stationary station to monitor the ecological state of the water area through the digitalization of plankton behavior.

Revised Iranian Water Quality Index (RIWQI): a tool for the assessment and management of water quality in Iran.

Water quality indices use biological, chemical, and physical data and information to classify the condition of surface waters, ultimately contributing to their management. We used multicollinearity and principal components analyses to develop the Revised Iranian Water Quality Index (RIWQI) as an indicator of agricultural and urban effects in the Karun River Basin of southwestern Iran. Seasonal sampling and analysis of water quality parameters from 54 sites across 18 rivers of the Karun River Basin include fecal coliform, total dissolved solid, phosphate, biological and chemical oxygen demand, nitrate, dissolved oxygen saturation, turbidity, pH, and water temperature. This study updates the previous version of Iranian Water Quality Index (IWQI) by differentially weighting individual variables, refining the main sub-indices, adding phosphate (PO4-), biological oxygen demand (BOD), chemical oxygen demand (COD), and temperature (T), and improving the aggregation calculation. Sensitivity testing of the RIWQI resulted in a mean value for discrimination efficiency (DE) > 85.6%, the highest of other indices calculated with the same dataset.

Autonomous Surface and Underwater Vehicles as Effective Ecosystem Monitoring and Research Platforms in the Arctic-The Glider Project.

Effective ocean management requires integrated and sustainable ocean observing systems enabling us to map and understand ecosystem properties and the effects of human activities. Autonomous subsurface and surface vehicles, here collectively referred to as "gliders", are part of such ocean observing systems providing high spatiotemporal resolution. In this paper, we present some of the results achieved through the project "Unmanned ocean vehicles, a flexible and cost-efficient offshore monitoring and data management approach-GLIDER". In this project, three autonomous surface and underwater vehicles were deployed along the Lofoten-Vesterålen (LoVe) shelf-slope-oceanic system, in Arctic Norway. The aim of this effort was to test whether gliders equipped with novel sensors could effectively perform ecosystem surveys by recording physical, biogeochemical, and biological data simultaneously. From March to September 2018, a period of high biological activity in the area, the gliders were able to record a set of environmental parameters, including temperature, salinity, and oxygen, map the spatiotemporal distribution of zooplankton, and record cetacean vocalizations and anthropogenic noise. A subset of these parameters was effectively employed in near-real-time data assimilative ocean circulation models, improving their local predictive skills. The results presented here demonstrate that autonomous gliders can be effective long-term, remote, noninvasive ecosystem monitoring and research platforms capable of operating in high-latitude marine ecosystems. Accordingly, these platforms can record high-quality baseline environmental data in areas where extractive activities are planned and provide much-needed information for operational and management purposes.

Underwater Holographic Sensor for Plankton Studies In Situ including Accompanying Measurements.

The paper presents an underwater holographic sensor to study marine particles-a miniDHC digital holographic camera, which may be used as part of a hydrobiological probe for accompanying (background) measurements. The results of field measurements of plankton are given and interpreted, their verification is performed. Errors of measurements and classification of plankton particles are estimated. MiniDHC allows measurement of the following set of background data, which is confirmed by field tests: plankton concentration, average size and size dispersion of individuals, particle size distribution, including on major taxa, as well as water turbidity and suspension statistics. Version of constructing measuring systems based on modern carriers of operational oceanography for the purpose of ecological diagnostics of the world ocean using autochthonous plankton are discussed. The results of field measurements of plankton using miniDHC as part of a hydrobiological probe are presented and interpreted, and their verification is carried out. The results of comparing the data on the concentration of individual taxa obtained using miniDHC with the data obtained by the traditional method using plankton catching with a net showed a difference of no more than 23%. The article also contains recommendations for expanding the potential of miniDHC, its purpose indicators, and improving metrological characteristics.

Use of pre-industrial baselines to monitor anthropogenic enrichment of metals concentrations in recently deposited sediment of floodplain lakes in the Peace-Athabasca Delta (Alberta, Canada).

Well-designed monitoring approaches are needed to assess effects of industrial development on downstream aquatic environments and guide environmental stewardship. Here, we develop and apply a monitoring approach to detect potential enrichment of metals concentrations in surficial lake sediments of the Peace-Athabasca Delta (PAD), northern Alberta, Canada. Since the ecological integrity of the PAD is strongly tied to river floodwaters that replenish lakes in the delta, and the PAD is located downstream of the Alberta oil sands, concerns have been raised over the potential transport of industry-supplied metals to the PAD via the Athabasca River. Surface sediment samples were collected in September 2017 from 61 lakes across the delta, and again in July 2018 from 20 of the same lakes that had received river floodwaters 2 months earlier, to provide snapshots of metals concentrations (Be, Cd, Cr, Cu, Ni, Pb, V, and Zn) that have recently accumulated in these lakes. To assess for anthropogenic enrichment, surficial sediment metals concentrations were normalized to aluminum and compared to pre-industrial baseline (i.e., reference) metal-aluminum linear relations for the Athabasca and Peace sectors of the PAD developed from pre-1920 measurements in lake sediment cores. Numerical analysis demonstrates no marked enrichment of these metals concentrations above pre-1920 baselines despite strong ability (> 99% power) to detect enrichment of 10%. Measurements of river sediment collected by the Regional Aquatics- and Oil Sands-Monitoring Programs (RAMP/OSM) also did not exceed pre-1920 concentrations. Thus, results presented here show no evidence of substantial oil sands-derived metals enrichment of sediment supplied by the Athabasca River to lakes in the PAD and demonstrate the usefulness of these methods as a monitoring framework.

Solar radiation and functional traits explain the decline of forest primary productivity along a tropical elevation gradient.

One of the major challenges in ecology is to understand how ecosystems respond to changes in environmental conditions, and how taxonomic and functional diversity mediate these changes. In this study, we use a trait-spectra and individual-based model, to analyse variation in forest primary productivity along a 3.3 km elevation gradient in the Amazon-Andes. The model accurately predicted the magnitude and trends in forest productivity with elevation, with solar radiation and plant functional traits (leaf dry mass per area, leaf nitrogen and phosphorus concentration, and wood density) collectively accounting for productivity variation. Remarkably, explicit representation of temperature variation with elevation was not required to achieve accurate predictions of forest productivity, as trait variation driven by species turnover appears to capture the effect of temperature. Our semi-mechanistic model suggests that spatial variation in traits can potentially be used to estimate spatial variation in productivity at the landscape scale.

Seasonal metabolic dynamics of microeukaryotic plankton: a year-long metatranscriptomic study in a temperate sea.

Seasonal fluctuations profoundly affect marine microeukaryotic plankton composition and metabolism, but accurately tracking these changes has been a long-standing challenge. In this study, we present a year-long metatranscriptomic data set from the Southern Bight of the North Sea, shedding light on the seasonal dynamics in temperate plankton ecosystems. We observe distinct shifts in active plankton species and their metabolic processes in response to seasonal changes. We characterized the metabolic signatures of different seasonal phases in detail, thereby revealing the metabolic versatility of dinoflagellates, the heterotrophic dietary strategy of Phaeocystis during its late-stage blooms, and stark variations in summer and fall diatom abundance and metabolic activity across nearby sampling stations. Our data illuminate the varied contributions of microeukaryotic taxa to biomass production and nutrient cycling at different times of the year and allow delineation of their ecological niches. IMPORTANCE: Ecosystem composition and metabolic functions of temperate marine microeukaryote plankton are strongly influenced by seasonal dynamics. Although monitoring of species composition of microeukaryotes has expanded recently, few methods also contain seasonally resolved information on ecosystem functioning. We generated a year-long spatially resolved metatranscriptomic data set to assess seasonal dynamics of microeukaryote species and their associated metabolic functions in the Southern Bight of the North Sea. Our study underscores the potential of metatranscriptomics as a powerful tool for advancing our understanding of marine ecosystem functionality and resilience in response to environmental changes, emphasizing its potential in continuous marine ecosystem monitoring to enhance our ecological understanding of the ocean's eukaryotic microbiome.

An integrated coastal ecosystem monitoring strategy: Pilot case in Naf-Saint Martin Peninsula, Bangladesh.

Rapid population growth creating an excessive pressure on the marine environment and thus monitoring of marine ecosystem is essential. However, due to high technical and financial involvement, monitoring of coastal ecosystem is always challenging in developing countries. This study aims to develop an integrated coastal ecosystem monitoring system that combines scientific sampling, numerical model simulation and citizen science observations to monitor the coastal ecosystem of Bangladesh. This concept of integrated monitoring approach was piloted from January 2022 to April 2023 at the South East coastal zone of Bangladesh. Scientific sampling and numerical model simulations were performed for temperature and salinity data collection. Citizen science approach was employed to collect data on environmental conditions, fisheries, plankton, other marine resources, and plastic pollution. Numerical model simulations and citizen scientists observations of temperature and salinity showed good agreement with the scientifically collected data. In addition, citizen scientists observations on fisheries, plankton, other marine resources and plastic pollution were also in line with the existing database and previous studies. The proposed integrated monitoring approach presents a viable technique, creating a new avenue for coastal and marine ecosystem monitoring where infrastructural facilities are limited.

Unveiling the role of taxonomic sufficiency for enhanced ecosystem monitoring.

The use of Artificial substrates (AS) as sampling devices addresses challenges in macrofaunal quantitative sampling. While effectively capturing biodiversity patterns, the time-intensitive identification process at the species level remains a substantial challenge. The Taxonomic Sufficiency approach (TS), where only taxa above species level are identified, arises as a potential solution to be tested across different environmental monitoring scenarios. In this paper, we analyzed three AS macrobenthic datasets to evaluate the odds of TS in improving the cost-effective ratio in AS monitoring studies and establish the highest resolution level to detect assemblage changes under different environmental factors. Results indicated that the family level emerged as a pragmatic compromise, balancing precision and taxonomic effort. Cost/benefit analysis supported TS efficiency, maintaining correlation stability until the family level. Results also showed that reducing resolution to family does not entail a significant Loss of Information. This study contributes to the discourse on TS applicability, highlighting its practicality in monitoring scenarios, including spatial-temporal studies, and rapid biodiversity assessments. Additionally, it highlights the "second best approach" of family-level practicality depending on the specific monitoring scenario and recognizes the importance of the species-level "best approach" before applying TS in monitoring studies.

Fabrication of graphene oxide-based pretreatment filter and Electrochemical-CRISPR biosensor for the field-ready cyanobacteria monitoring system.

Microcystis aeruginosa (M. aeruginosa) cause the eutrophication of lakes and rivers. To effectively control the overgrowth of M. aeruginosa, a suitable measurement method should be required in the aquatic fields. To address this, we developed a field-ready cyanobacterial pretreatment device and an electrochemical clustered regularly interspaced short palindromic repeats (EC-CRISPR) biosensor. The cyanobacterial pretreatment device consists of a syringe, glass bead, and graphene oxide (GO) bead. Then, the M. aeruginosa dissolved in the freshwater sample was added to fabricated filter. After filtration, the purified gene was loaded onto a CRISPR-based electrochemical biosensor chip to detect M. aeruginosa gene fragments. The biosensor was composed of CRISPR/Cpf1 protein conjugated with MXene on an Au microgap electrode (AuMGE) integrated into a printed circuit board (PCB). This AuMGE/PCB system maximizes the signal-to-noise ratio, which controls the working and counter electrode areas requiring only 3 µL samples to obtain high reliability. Using the extracted M. aeruginosa gene with a pre-treatment filter, the CRISPR biosensor showed a limit of detection of 0.089 pg/µl in fresh water. Moreover, selectivity test and matrix condition test carried out using the EC-CRISPR biosensor. These handheld pre-treatment kit and biosensors can enable field-ready detection of CyanoHABs.

Ecosystem responses of shallow thermokarst lakes to climate-driven hydrological change: Insights from long-term monitoring of periphytic diatom community composition at Old Crow Flats (Yukon, Canada).

Shallow waterbodies are abundant in Arctic and subarctic landscapes where they provide productive wildlife habitat and hold cultural and socioeconomic importance for Indigenous communities. Their vulnerability to climate-driven hydrological and limnological changes enhances a need for long-term monitoring data capable of tracking aquatic ecosystem responses. Here, we evaluate biological and inferred physicochemical responses associated with a rise in rainfall-generated runoff and increasingly positive lake water balances in Old Crow Flats (OCF), a 5600 km2 thermokarst landscape in northern Yukon. This is achieved by analyzing periphytic diatom community composition in biofilms accrued on artificial-substrate samplers at 14 lakes collected mostly annually during 2008-2019 CE. Results reveal that diatom communities at 10 of the 14 lakes converged toward a composition typical of lakes with rainfall-dominated input waters. These include six of nine lakes that were not initially dominated by rainfall input. The shifts in diatom community composition infer rise of lake-water pH and ionic content, and they reveal that northern shallow lake ecosystems are responsive to climate-driven increases in rainfall. Based on data generated during the 12 -year-long monitoring period, we conclude that lakes located centrally within OCF are most vulnerable to rapid climate-driven hydroecological change due to flat terrain, larger lake surface area, and sparse terrestrial vegetation, which provide less resistance to lake expansion, shoreline erosion, and sudden drainage. This information assists the local Indigenous community and natural resource stewardship agencies to anticipate changes to traditional food sources and inform adaptation options.

Evaluating biodiversity for coral reef reformation and monitoring on complex 3D structures using environmental DNA (eDNA) metabarcoding.

Quantifying coral reef biodiversity is challenging for cryptofauna and organisms in early life stages. We demonstrate the utility of eDNA metabarcoding as a tool for comprehensively evaluating invertebrate communities on complex 3D structures for reef reformation, and the role these structures play in provisioning habitat for organisms. 3D design and printing were used to create 18 complex tiles, which were used to form artificial reef structures. eDNA was collected from scraping tile surfaces for organismal biomass and from seawater samples around the artificial reefs in the Gulf of Eilat/Aqaba, Red Sea. Metabarcoding targeted the mitochondrial COI gene with specific primers for marine biodiversity. We provide the first eDNA biodiversity baseline for the Gulf of Eilat/Aqaba, capturing extensive information on species abundance, richness, and diversity. Tile tops had higher phylogenetic diversity and richness, despite a higher abundance of organisms on tile bottoms, highlighting the detection of cryptic organisms with eDNA. We recommend eDNA metabarcoding for reef restoration initiatives, especially for complex marine structures, to improve success and evaluation of biodiversity.

How to quantify algal turf sediments and particulates on tropical and temperate reefs: An overview.

Algal turfs are the most abundant benthic covering on reefs in many shallow-water marine ecosystems. The particulates and sediments bound within algal turfs can influence a multitude of functions within these ecosystems. Despite the global abundance and importance of algal turfs, comparison of algal turf-bound sediments is problematic due to a lack of standardisation across collection methods. Here we provide an overview of three methods (vacuum sampling, airlift sampling, and TurfPods), and the necessary equipment (including construction suggestions), commonly employed to quantify sediments from algal turfs. We review the purposes of these methods (e.g. quantification of standing stock versus net accumulation) and how methods can vary depending on the research question or monitoring protocol. By providing these details in a readily accessible format we hope to encourage a standardised set of approaches for marine benthic ecologists, geologists and managers, that facilitates further quantification and global comparisons of algal turf sediments.

Spatial Pattern and Dynamic Change of Vegetation Greenness From 2001 to 2020 in Tibet, China.

Due to the cold climate and dramatically undulating altitude, the identification of dynamic vegetation trends and main drivers is essential to maintain the ecological balance in Tibet. The normalized difference vegetation index (NDVI), as the most commonly used greenness index, can effectively evaluate vegetation health and spatial patterns. MODIS-NDVI (Moderate-resolution Imaging Spectroradiometer-NDVI) data for Tibet from 2001 to 2020 were obtained and preprocessed on the Google Earth Engine (GEE) cloud platform. The Theil-Sen median method and Mann-Kendall test method were employed to investigate dynamic NDVI changes, and the Hurst exponent was used to predict future vegetation trends. In addition, the main drivers of NDVI changes were analyzed. The results indicated that (1) the vegetation NDVI in Tibet significantly increased from 2001 to 2020, and the annual average NDVI value fluctuated between 0.31 and 0.34 at an increase rate of 0.0007 year-1; (2) the vegetation improvement area accounted for the largest share of the study area at 56.6%, followed by stable unchanged and degraded areas, with proportions of 27.5 and 15.9%, respectively. The overall variation coefficient of the NDVI in Tibet was low, with a mean value of 0.13; (3) The mean value of the Hurst exponent was 0.53, and the area of continuously improving regions accounted for 41.2% of the study area, indicating that the vegetation change trend was continuous in most areas; (4) The NDVI in Tibet indicated a high degree of spatial agglomeration. However, there existed obvious differences in the spatial distribution of NDVI aggregation areas, and the aggregation types mainly included the high-high and low-low types; and (5) Precipitation and population growth significantly contributed to vegetation cover improvement in western Tibet. In addition, the use of the GEE to obtain remote sensing data combined with time-series data analysis provides the potential to quickly obtain large-scale vegetation change trends.

Automated mapping of Portulacaria afra canopies for restoration monitoring with convolutional neural networks and heterogeneous unmanned aerial vehicle imagery.

Ecosystem restoration and reforestation often operate at large scales, whereas monitoring practices are usually limited to spatially restricted field measurements that are (i) time- and labour-intensive, and (ii) unable to accurately quantify restoration success over hundreds to thousands of hectares. Recent advances in remote sensing technologies paired with deep learning algorithms provide an unprecedented opportunity for monitoring changes in vegetation cover at spatial and temporal scales. Such data can feed directly into adaptive management practices and provide insights into restoration and regeneration dynamics. Here, we demonstrate that convolutional neural network (CNN) segmentation algorithms can accurately classify the canopy cover of Portulacaria afra Jacq. in imagery acquired using different models of unoccupied aerial vehicles (UAVs) and under variable light intensities. Portulacaria afra is the target species for the restoration of Albany Subtropical Thicket vegetation, endemic to South Africa, where canopy cover is challenging to measure due to the dense, tangled structure of this vegetation. The automated classification strategy presented here is widely transferable to restoration monitoring as its application does not require any knowledge of the CNN model or specialist training, and can be applied to imagery generated by a range of UAV models. This will reduce the sampling effort required to track restoration trajectories in space and time, contributing to more effective management of restoration sites, and promoting collaboration between scientists, practitioners and landowners.

The new Seafloor Observatory (OBSEA) for remote and long-term coastal ecosystem monitoring.

A suitable sampling technology to identify species and to estimate population dynamics based on individual counts at different temporal levels in relation to habitat variations is increasingly important for fishery management and biodiversity studies. In the past two decades, as interest in exploring the oceans for valuable resources and in protecting these resources from overexploitation have grown, the number of cabled (permanent) submarine multiparametric platforms with video stations has increased. Prior to the development of seafloor observatories, the majority of autonomous stations were battery powered and stored data locally. The recently installed low-cost, multiparametric, expandable, cabled coastal Seafloor Observatory (OBSEA), located 4 km off of Vilanova i la Gertrú, Barcelona, at a depth of 20 m, is directly connected to a ground station by a telecommunication cable; thus, it is not affected by the limitations associated with previous observation technologies. OBSEA is part of the European Multidisciplinary Seafloor Observatory (EMSO) infrastructure, and its activities are included among the Network of Excellence of the European Seas Observatory NETwork (ESONET). OBSEA enables remote, long-term, and continuous surveys of the local ecosystem by acquiring synchronous multiparametric habitat data and bio-data with the following sensors: Conductivity-Temperature-Depth (CTD) sensors for salinity, temperature, and pressure; Acoustic Doppler Current Profilers (ADCP) for current speed and direction, including a turbidity meter and a fluorometer (for the determination of chlorophyll concentration); a hydrophone; a seismometer; and finally, a video camera for automated image analysis in relation to species classification and tracking. Images can be monitored in real time, and all data can be stored for future studies. In this article, the various components of OBSEA are described, including its hardware (the sensors and the network of marine and land nodes), software (data acquisition, transmission, processing, and storage), and multiparametric measurement (habitat and bio-data time series) capabilities. A one-month multiparametric survey of habitat parameters was conducted during 2009 and 2010 to demonstrate these functions. An automated video image analysis protocol was also developed for fish counting in the water column, a method that can be used with cabled coastal observatories working with still images. Finally, bio-data time series were coupled with data from other oceanographic sensors to demonstrate the utility of OBSEA in studies of ecosystem dynamics.

Pesticides are the dominant stressors for vulnerable insects in lowland streams.

Despite elaborate regulation of agricultural pesticides, their occurrence in non-target areas has been linked to adverse ecological effects on insects in several field investigations. Their quantitative role in contributing to the biodiversity crisis is, however, still not known. In a large-scale study across 101 sites of small lowland streams in Central Europe, Germany we revealed that 83% of agricultural streams did not meet the pesticide-related ecological targets. For the first time we identified that agricultural nonpoint-source pesticide pollution was the major driver in reducing vulnerable insect populations in aquatic invertebrate communities, exceeding the relevance of other anthropogenic stressors such as poor hydro-morphological structure and nutrients. We identified that the current authorisation of pesticides, which aims to prevent unacceptable adverse effects, underestimates the actual ecological risk as (i) measured pesticide concentrations exceeded current regulatory acceptable concentrations in 81% of the agricultural streams investigated, (ii) for several pesticides the inertia of the authorisation process impedes the incorporation of new scientific knowledge and (iii) existing thresholds of invertebrate toxicity drivers are not protective by a factor of 5.3 to 40. To provide adequate environmental quality objectives, the authorisation process needs to include monitoring-derived information on pesticide effects at the ecosystem level. Here, we derive such thresholds that ensure a protection of the invertebrate stream community.

Crop Nitrogen Retrieval Methods for Simulated Sentinel-2 Data Using In-Field Spectrometer Data.

Nitrogen (N) is one of the key nutrients supplied in agricultural production worldwide. Over-fertilization can have negative influences on the field and the regional level (e.g., agro-ecosystems). Remote sensing of the plant N of field crops presents a valuable tool for the monitoring of N flows in agro-ecosystems. Available data for validation of satellite-based remote sensing of N is scarce. Therefore, in this study, field spectrometer measurements were used to simulate data of the Sentinel-2 (S2) satellites developed for vegetation monitoring by the ESA. The prediction performance of normalized ratio indices (NRIs), random forest regression (RFR) and Gaussian processes regression (GPR) for plant-N-related traits was assessed on a diverse real-world dataset including multiple crops, field sites and years. The plant N traits included the mass-based N measure, N concentration in the biomass (Nconc), and an area-based N measure approximating the plant N uptake (NUP). Spectral indices such as normalized ratio indices (NRIs) performed well, but the RFR and GPR methods outperformed the NRIs. Key spectral bands for each trait were identified using the RFR variable importance measure and the Gaussian processes regression band analysis tool (GPR-BAT), highlighting the importance of the short-wave infrared (SWIR) region for estimation of plant Nconc-and to a lesser extent the NUP. The red edge (RE) region was also important. The GPR-BAT showed that five bands were sufficient for plant N trait and leaf area index (LAI) estimation and that a surplus of bands effectively reduced prediction performance. A global sensitivity analysis (GSA) was performed on all traits simultaneously, showing the dominance of the LAI in the mixed remote sensing signal. To delineate the plant-N-related traits from this signal, regional and/or national data collection campaigns producing large crop spectral libraries (CSL) are needed. An improved database will likely enable the mapping of N at the agro-ecosystem level or for use in precision farming by farmers in the future.