Water evaporation represents a major source of water loss in agricultural systems, particularly in arid and semi-arid regions. Developing innovative, data-driven approaches to quantify and manage evaporation is therefore essential for sustainable water resource management. This study proposes an original experimental protocol combined with machine learning techniques to support smart evaporation management at the plot scale.

The experimental setup consists of two identical artificial basins exposed to the same climatic conditions: one partially covered by a photovoltaic panel, while the other remains uncovered. Continuous high-resolution measurements of water level variations, along with other climatic parameters (humidity, air temperature, water temperature, TDS, etc.), are collected using sensors, enabling a precise characterization of evaporation dynamics under contrasting surface conditions.

The acquired experimental data constitute a dedicated database for training machine learning models, including Support Vector Machines (SVM), Gradient Boosting, and Random Forest, aimed at predicting evaporation rates and identifying the main controlling factors. According to the results, the Gradient Boosting model performed best, achieving an R² of 0.993 and RMSE of 0.245 for the open basin, and an R² of 0.996 and RMSE of 0.158 for the covered basin, indicating highly accurate predictions. Random Forest and SVM were also tested, showing good and poor predictive performance, respectively.These findings demonstrate the reliability of ensemble models, particularly Gradient Boosting, for modeling evaporation from measured climatic parameters. The models support adaptive irrigation strategies and contribute to the development of an intelligent agricultural plot, where water losses can be anticipated and minimized.

This work highlights the potential of coupling experimental hydrological observations with machine learning to reduce evaporation losses while promoting the integration of renewable energy solutions in agricultural water management.
key words: Water evaporation,Climate Change,Machine Learning,Experimental protocol,Photovoltaic covering, Smart agricultural plot

How to cite: ouchkir, I., Arioua, A., Arioua, B., Karaoui, I., Nait-taleb, O., El Kamouni, F. E., and Bimouhen, M.: An Experimental Protocol Combined with machine mearning for Smart Evaporation Management under Climate Change, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-4527, https://doi.org/10.5194/egusphere-egu26-4527, 2026.

Saline lakes play a critical role in ecosystem functioning and are highly sensitive to both 
climatic variability and human-induced pressures. Rising global water demand and intensified 
water extraction coupled with shifts in precipitation regimes and increasing temperatures 
have altered the hydrological stability of many saline lakes across the world. This study 
integrates satellite remote sensing and multi-decadal historical observations to assess the 
spatial extent and long-term dynamics of more than 24,000 saline lakes (> 10 ha) worldwide 
from 1985 to 2021. Our preliminary results reveal that approximately 15% of these lakes have 
undergone notable shrinkage, about 31% have experienced expansion, and the rest have 
remained largely unchanged during the study period. Linking spatial trends to climatic regimes 
indicates that lake shrinkage is primarily concentrated in arid and semi-arid regions which 
often experience acute water stress problems. In contrast, accelerated snow and glacier melt 
with global warming has been a primary driver of lake expansion. These findings underscore 
the need for region-specific water management strategies, especially in water-stressed 
regions where lake desiccation enhances ecosystem degradation and dust emissions with 
significant human health implications (Hassani et al., 2020).

Hassani, A., Azapagic, A., D'Odorico, P., Keshmiri, A., Shokri, N. (2020). Desiccation crisis of 
saline lakes: A new decision-support framework for building resilience to climate change. 
Science of the Total Environment, 703, 134718,
https://doi.org/10.1016/j.scitotenv.2019.134718

How to cite: Kumaraswamy, I., Aminzadeh, M., and Shokri, N.: A global assessment of saline lake dynamics from 1985 to 2021, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-6863, https://doi.org/10.5194/egusphere-egu26-6863, 2026.

Lakes and reservoirs support rich biodiversity and are essential for the natural production of over 12% of Germany's drinking water. Their biodiversity is crucial for maintaining water quality but is increasingly threatened by climate change, pollution and the spread of invasive species. In the context of the IQ Water project, a multifaceted approach is employed to assess water quality, encompassing conventional parameters such as physical, chemical, and hygienic metrics, as well as assessments of the planktonic community, in conjunction with innovative molecular methodologies (e.g., eDNA analyses). This integrated strategy enables the exploration of reservoir behavior across multiple dimensions, including physicochemical aspects, in addition to the often-overlooked domain of microbial biodiversity, encompassing bacteria, viruses, protozoa, and fungi. The focus of this research is on water quality parameters, including, but not limited to blooms of potentially toxic cyanobacteria or hygienic relevant bacteria, antibiotic resistance genes (ARG), viruses, and invasive species. The overarching objective of the project is to develop biodiversity models for drinking water reservoirs by integrating complex biological, chemical, and physical data with machine learning (ML) technologies. These ML models aim to enable the prediction of important hygienic challenges like cyanobacterial blooms and the distribution of pathogens and ARGs, thereby contributing to the advancement of understanding of aquatic freshwater ecosystem dynamics.

In this contribution, we present preliminary findings regarding the efficacy of molecular methodologies in analyzing reservoir biodiversity. We also offer insights from a data-centric perspective, including the necessity of a unified data schema for the collection of highly heterogeneous data and the support of machine learning (ML)-based modeling. We showcase ML-based cross-reservoir assessments for ecosystem monitoring based on the proposed framework by modeling biochemical and physicochemical fingerprints. Furthermore, we propose a neural network–based multi‑resolution modelling approach that explicitly accounts for strongly variable sampling intervals (hours to months) within a single model. The architecture treats meteorological and physicochemical time series as primary sequential inputs and uses sparsely sampled molecular profiles as contextual information via learned embeddings and cross‑attention.

How to cite: Wunsch, A., Kühnert, C., Holzer, C., Ho, J., and Hügler, M.: IQ Water: AI-supported modeling and forecasting of biodiversity and water quality in drinking water reservoirs, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-7826, https://doi.org/10.5194/egusphere-egu26-7826, 2026.

Climate change, population growth, and water source pollution present significant challenges for water resource managers, who often face limited resources and scarce in-situ data in the arid and semi-arid regions of Sub-Saharan Africa. In Kenya, about 80% of the country’s land area falls within these arid and semi-arid regions. These areas support 36% of the human population and 70% of the livestock population, contributing roughly 50% of agricultural GDP and 15% of national GDP. Water pans, which are small, shallow reservoirs that fill with surface runoff, sustain local livelihoods by supplying water for livestock, wildlife, and small-scale agropastoral irrigation. However, water pans are becoming increasingly susceptible to climate change, highlighting the need for continuous monitoring to ensure water availability for communities. Remote sensing provides a valuable complement to traditional water monitoring techniques by offering spatially extensive and repeatable observations that enhance our understanding of water dynamics. In this context, our primary aims were to evaluate the potential of Sentinel-2 imagery for detecting water presence and assessing physicochemical parameters, specifically turbidity and specific conductivity, in water pans in Taita Taveta County, Kenya. We employed mid-point and receiver operating characteristic (ROC) curve-based threshold methods for water presence detection, alongside generalized additive models for estimating turbidity and specific conductivity. We achieved an F1 score greater than 95% for water presence detection using the Normalized Difference Moisture Index and the two thresholds. The B8A/B4 predictor for specific conductivity yielded a coefficient of determination (R²) of less than 0.5 with both standard and group leave-one-out cross-validation (LOOCV). In contrast, the B8/B4 and B8/B5 predictors for turbidity recorded R² values greater than 0.8 with standard LOOCV and greater than 0.6 with group LOOCV. Overall, this study demonstrates the potential of remote sensing-based approaches for water monitoring, even under conditions of limited data availability.

How to cite: Ogola, P., Heiskanen, J., Too, A., Mundia, C., Gettel, G., and Pellikka, P.: Remote sensing of water presence and physicochemical parameters in water pans in semi-arid Kenya using Sentinel-2 imagery, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-9551, https://doi.org/10.5194/egusphere-egu26-9551, 2026.

Human-driven nutrient enrichment is accelerating the spread of invasive aquatic macrophytes, generating substantial ecological and socio-economic impacts in freshwater ecosystems, including biodiversity loss, deterioration of drinking water quality, reduced fisheries productivity, constraints on recreational use as well as impaired waterborne transport. Consequently, the management of invasive aquatic weeds is now widely regarded as a priority for the conservation and sustainable use of freshwater lakes.

This study critically reviews the main control strategies currently adopted to limit the expansion of highly invasive species such as Salvinia molesta, Eichhornia crassipes, Egeria densa, Pistia stratiotes, and Elodea nuttallii. Starting from 30,659 academic and grey literature articles matching our search criteria across multiple browsers (i.e. Google Scholar, ProQuest, Web of Science, and Scopus), we critically analysed 155 fully relevant articles, focusing on lake morphology, infestation details (year of detection and species involved), strategy characteristics and their effectiveness (reduction in surface coverage and containment in the event of reappearance), as well as the qualitative and quantitative advantages and disadvantages of each method.

Our work also examines the global distribution of such management practices and integrates satellite-based remote sensing data to quantify macrophyte surface coverage in lake environments pre‑ and post‑control. Our results to date have identified three dominant approaches: mechanical removal (in 15.6% of the cases), chemical herbicide application (19.5%), and biological control (28.6%), alongside integrated management combining the former approaches (28.6%) and other treatments (7.8%).

Mechanical harvesting and chemical treatments can rapidly reduce biomass, yet their long-term application is often constrained by high operational costs and, in the case of herbicides, potential environmental risks. Biological control, typically involving specialist insects or herbivorous fish, appears to offer a more sustainable and self-maintaining option (with a recurrence rate of 11.4% of the cases, compared with 33.3% for chemical approaches and 41.7% for mechanical treatments), although its effectiveness depends on predator–prey specificity and the suitability of local climatic conditions.

In terms of geographical distribution, the case studies were unevenly distributed, with 40.8% located in North America (which shows a predominance of chemical treatment accounting for 36.7% of the total, particularly in the United States), 25.0% in Africa (where 70.0% of the cases involved biocontrol), and a smaller share in Oceania and Asia (representing 20.0% and 10.8% of the total, respectively), with an even smaller proportion in Europe and South America.

By comparing the strengths, limitations, and context-dependent requirements of each method, this study supports the selection of appropriate management strategies for future case studies, taking into account ecological characteristics, invasion dynamics, geographic setting, and available economic resources.

How to cite: Reboldi, M., Bertone, E., Valerio, G., O'Halloran, K., and Purcell, M.: Comparative Assessment of Management Strategies for Invasive Aquatic Macrophytes in Freshwater Lakes, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-15870, https://doi.org/10.5194/egusphere-egu26-15870, 2026.

Endorheic lakes, terminal basins without surface outflows, are among the most sensitive indicators of hydroclimatic change. While recent global analyses have highlighted widespread shrinkage driven by a combination of anthropogenic and climatic factors, many endorheic lakes have remained stable or even expanded over the past two decades. We hypothesize that understanding the mechanisms behind their resilience can help adaptive water management and conservation strategies in closed basins. Building on our global assessment of 635 endorheic lakes (Nevermann et al., 2025), which identified 130 lakes exhibiting significant shrinkage, here we focus on the remaining non-shrinking systems to determine how they persist under increasing hydroclimatic stress. Using multi-decadal satellite records, land-use data, and climate reanalysis, we aim to quantify decadal hydrological stability trends (for 2000 to 2021). A comparison of stable versus shrinking lakes across climate zones, water-stress categories, and basin-level anthropogenic activity will help disentangle resilience mechanisms such as increased glacial melt contributions, climatic water surpluses, effective basin management, and limited irrigation pressures. Preliminary findings indicate that many stable lakes occur in high-elevation basins (e.g., Tibetan Plateau, Andes), where increased cryospheric water input offsets evaporative losses, while others in semi-arid regions exhibit stability linked to strong governance or reduced agricultural intensity. These contrasting hydrological trajectories provide valuable insights into how natural and managed systems maintain equilibrium under global change.

Nevermann, H., Aminzadeh, M., Madani, K., D’Odorico, P., AghaKouchak, A., & Shokri, N. (2025). A global perspective on endorheic lake shrinkage: Impacts of anthropogenic and atmospheric factors. EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-8774. https://doi.org/10.5194/egusphere-egu25-8774

How to cite: Nevermann, H., Aminzadeh, M., Or, D., and Shokri, N.: Why some terminal lakes remain stable while others shrink under hydroclimatic stresses?, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-18717, https://doi.org/10.5194/egusphere-egu26-18717, 2026.

The “Kefalari Agios Ioannis” spring, situated at approximately 871 m elevation and about 1,650 m south-southeast of the picturesque village of Dimitsana (Peloponnesus, Greece), is used for both drinking water supply and irrigation.

The spring is a contact spring, discharging the karst aquifer developed in the Upper Cretaceous platy limestones of the Pindos Unit, at their contact with the underlying impermeable red cherts, siltstones, and “First Flysch” (Upper Jurassic – Lower Cretaceous) of the same unit.

The recession coefficient of the “Kefalari Agios Ioannis” spring, calculated from flow measurements conducted between 14 July 2024 (711.1 m³/h) and 27 October 2024 (69.4 m³/h), is 8.69 × 10^-³ days^-¹. This value indicates that groundwater flow occurs mainly through fractures and intra-stratigraphic voids within the Upper Cretaceous platy limestones of the Pindos Unit. The calculated recession coefficient is consistent with values reported in the literature for karst aquifers developed in the Pindos Unit and equivalent formations, which are on the order of 10^-³ days^-¹ (Soulios, 1985; Giannatos, 1999; Karalemas, 2010).

The hydrological year 2023-2024 was particularly dry (1,109.2 mm), and the calculated recession coefficient should therefore be interpreted with caution, as it reflects flow conditions under prolonged drought and water scarcity. Such conditions may alter groundwater circulation, which is not uniform across the hydrogeological basin and becomes more evident under extreme hydrological conditions—either surplus (wet years) or deficit (dry years)—when different sections and levels of the recharge area are activated or operate differently. Notably, the recession period lasted at least 105 days. The following hydrological year, 2024-2025, was also dry (1,135.6 mm), in contrast to the wetter years 2021-2022 and 2022-2023, which recorded precipitation totals of 1,436.4 mm and 1,426.6 mm, respectively. For the ongoing 2025-2026 hydrological year, a total of 602.4 mm of precipitation has been recorded as of 14 January, indicating that dry conditions persist.

Effective water resources management should prioritize the protection and zoning of the karst aquifer, include systematic monitoring of spring discharge and groundwater quality, regulated and sustainable planning of groundwater abstraction through controlled boreholes, and the enhancement of natural and artificial recharge where feasible. Such adaptation measures are essential to mitigate the impacts of extreme hydrological events and prolonged droughts, ensuring the long-term availability of water for both human consumption and downstream cultural heritage sites.

Under the currently observed low-discharge conditions (98.2 m³/h as of 7 August 2024), the operation of the Open-Air Water Power Museum of the Piraeus Cultural Foundation, which is located immediately downstream, is significantly affected, as the available spring flow becomes insufficient during the summer months. Consequently, the museum is periodically forced to suspend its operation, highlighting the direct dependence of cultural and touristic activities on the hydrological regime of the “Kefalari Agios Ioannis” spring.

In conclusion, the sustainable management of water resources in the Dimitsana area, and particularly of the karst aquifer discharged by the “Kefalari Agios Ioannis” spring, is imperative given the combined pressures of ongoing tourism development and climate variability.

How to cite: Korovesai, A., Filis, C., Skourtsos, E., Andreadakis, E., Kapourani, E., Karalemas, N., and Alexopoulos, A.: Water Resources Management of the “Kefalari Agios Ioannis” Spring, Dimitsana, Greece, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-20614, https://doi.org/10.5194/egusphere-egu26-20614, 2026.

Three main aquifer systems have developed on Kythira Island (Greece) (Pagounis, 1981; Pagounis & Gertsos, 1984; Danamos, 1991; Koumantakis et al., 2006; Filis et al., 2019):

• The porous aquifer system within Neogene and Quaternary formations.
• The karst aquifer system developed in the carbonate formations of the Pindos and Tripolitza Units.
• The aquifer system, both shallow and deep, within fractured hard rocks, mainly associated with the Phyllites – Quartzites Unit.

The main discharge of the aquifer systems takes place in coastal and submarine brackish springs around the island, except for its northern part where the Phyllites – Quartzites Unit outcrops and its central part where springs of small capacity discharge the carbonate formations of the Pindos Unit.

Precipitation is the direct recharge of the three aforementioned aquifer systems while indirectly lateral discharge occurs in places between adjacent and tangential aquifer systems and from the streams runoff as well.

The municipal water supply of Kythira has been reinforced by a series of projects and interventions, focusing on the summer touristic period, mainly consisting of new deep boreholes and low-capacity desalination plants.

The climate crisis has led to increasingly frequent high-intensity hydro-meteorological events, particularly in summer, with heavy rainfall over short periods. Consequently:

• Surface runoff dominates, limiting groundwater recharge.
• Evapotranspiration increases due to high temperatures and longer daylight hours.

Taking the above into consideration, the following conclusions can be drawn regarding the water resources of Kythira:

• The coverage of water supply needs during the summer months faces severe challenges, with frequent interruptions in water distribution.
• Overexploitation of available water resources occurs during the summer months, due to the significant increase in population and the inability to meet water demand, as a result of the substantial tourism development in recent years.
• During the period of maximum water demand (summer months), the available water supply is at its minimum.
• The climate crisis has adversely affected the recharge of individual aquifers.
• The drilling of new water-supply boreholes does not always yield the desired results, due to the area’s particular hydrogeological structure.
• Water resources management in Kythira presents a pessimistic outlook, as the projected changes in mean seasonal and average climatic parameters are negative, indicating decreased precipitation accompanied by increased temperatures.

In conclusion, there is an urgent need to implement actions and interventions for the sustainable management of the water resources of Kythira, which, depending on local conditions, may include the following:

• Proposals/measures for the rational management of groundwater resources at the Community level (environmental awareness, drilling of water-supply boreholes, desalination plant locations, protection zones for municipal water abstraction works, etc.).
• Siting of small check dams along watercourses to regulate downstream flow and promote artificial recharge.
• Siting of small reservoirs within and/or outside watercourses for the storage of winter runoff, as well as identification of locations for drilling boreholes for the implementation of artificial recharge, under specific conditions.

How to cite: Zoumbourlis, G., Filis, C., Skourtsos, E., Megalokonomou, E., Ketsetsioglou, V., and Trianti, N.: Water Resources Management in Kythira Island (Greece) under High Tourism Pressure and Climate Crisis, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-20903, https://doi.org/10.5194/egusphere-egu26-20903, 2026.