Analyzing variation of water inflow to inland lakes under climate change: Integrating deep learning and time series data mining.

The alarming depletion of global inland lakes in recent decades makes it essential to predict water inflow from rivers to lakes (WIRL) trend and unveil the dominant influencing driver, particularly in the context of climate change. The raw time series data contains multiple components (i.e., long-term trend, seasonal periodicity, and random noise), which makes it challenging for traditional machine/deep learning techniques to effectively capture long-term trend information. In this study, a novel FactorConvSTLnet (FCS) method is developed through integrating STL decomposition, convolutional neural networks (CNN), and factorial analysis into a general framework. FCS is more robust in long-term WIRL trend prediction through separating trend information as a modeling predictor, as well as unveiling predominant drivers. FCS is applied to typical inland lakes (the Aral Sea and the Lake Balkhash) in Central Asia, and results indicate that FCS (Nash-Sutcliffe efficiency = 0.88, root mean squared error = 67m³/s, mean relative error = 10%) outperforms the traditional CNN. Some main findings are: (i) during 1960-1990, reservoir water storage (WSR) was the dominant driver for the two lakes, respectively contributing to 71% and 49%; during 1991-2014 and 2015-2099, evaporation (EVAP) would be the dominant driver, with the contribution of 30% and 47%; (ii) climate change would shift the dominant driver from human activities to natural factors, where EVAP and surface snow amount (SNW) have an increasing influence on WIRL; (iii) compared to SSP1-2.6, the SNW contribution would decrease by 26% under SSP5-8.5, while the EVAP contribution would increase by 9%. The findings reveal the main drivers of shrinkage of the inland lakes and provide the scientific basis for promoting regional ecological sustainability.

Water resource dynamics and protection strategies for inland lakes: A case study of Hongjiannao Lake.

Globally, lakes are drying up and shrinking and inland lakes, in particular, face severe water shortage problems. Thus, the degradation mechanisms and protection measures for inland lakes urgently need to be explored. Hongjiannao Lake (HL), an inland lake on the border of Shaanxi Province and Inner Mongolia Autonomous Region of China, was selected for the present case study. The evolution of HL was analyzed and the current lake water storage was measured on site. The driving factors of water resource changes in HL were discussed based on meteorological and landcover data. The results showed that (1) from 1929 to 2021, the lake area of HL experienced four stages: formation, stability, shrinkage and recovery. The smallest water area was 31.08 km2 in 2015, half the size of lake in the 1960s. (2) Spatially, the morphological changes of HL mainly occurred where the rivers entered the lake. (3) In 2021, the average depth of HL was 3.77 m, and the water storage capacity was 140.56 million m3. (4) The annual average evaporation was 3.36 times the amount of the annual average precipitation in Hongjiannao Basin (HB), but climate change was not the main driver of changes in the HL area. (5) In the past 20 years, cultivated land and artificial surface increased by 3.11% and 1.04%, respectively, whereas grassland and water body decreased by 3.51% and 0.45%, respectively. The expansion of cultivated land and artificial surface, as well as the construction of reservoirs upstream of the lake, hindered the replenishment of water resources to HL. This study recommends a range of strategies for water resource protection in inland lakes, including implementing ecological restoration projects, carrying out inter-basin water transfer measures, improving the efficiency of regional water resource use, and improving industrial structure and distribution.

Mapping particulate organic carbon in lakes across China using OLCI/Sentinel-3 imagery.

Remote sensing monitoring of particulate organic carbon (POC) concentration is essential for understanding phytoplankton productivity, carbon storage, and water quality in global lakes. Some algorithms have been proposed, but only for regional eutrophic lakes. Based on in-situ data (N = 1269) in 49 lakes across China, we developed a blended POC algorithm by distinguishing Type-I and Type-II waters. Compared to Type-I, Type-II waters had higher reflectance peak around 560 nm (>0.0125 sr-1) and mean POC (4.65 ± 4.11 vs. 2.66 ± 3.37 mg/L). Furthermore, because POC was highly related to algal production (r = 0.85), a three-band index (R2 = 0.65) and the phytoplankton fluorescence peak height (R2 = 0.63) were adopted to estimate POC in Type-I and Type-II waters, respectively. The novel algorithm got a mean absolute percent difference (MAPD) of 35.93 % and outperformed three state-of-the-art formulas with MAPD values of 40.56-76.42 %. Then, the novel algorithm was applied to OLCI/Sentinel-3 imagery, and we first obtained a national map of POC in 450 Chinese lakes (> 20 km2), which presented an apparent spatial pattern of "low in the west and high in the east". In brief, water classification should be considered when remotely monitoring lake POC concentration over a large area. Moreover, a process-oriented method is required when calculating water column POC storage from satellite-derived POC concentrations in type-II waters. Our results contribute substantially to advancing the dynamic observation of the lake carbon cycle using satellite data.

Quantification of Diffusive Methane Emissions from a Large Eutrophic Lake with Satellite Imagery.

Lakes are major emitters of methane (CH4); however, a longstanding challenge with quantifying the magnitude of emissions remains as a result of large spatial and temporal variability. This study was designed to address the issue using satellite remote sensing with the advantages of spatial coverage and temporal resolution. Using Aqua/MODIS imagery (2003-2020) and in situ measured data (2011-2017) in eutrophic Lake Taihu, we compared the performance of eight machine learning models to predict diffusive CH4 emissions and found that the random forest (RF) model achieved the best fitting accuracy (R2 = 0.65 and mean relative error = 21%). On the basis of input satellite variables (chlorophyll a, water surface temperature, diffuse attenuation coefficient, and photosynthetically active radiation), we assessed how and why they help predict the CH4 emissions with the RF model. Overall, these variables mechanistically controlled the emissions, leading to the model capturing well the variability of diffusive CH4 emissions from the lake. Additionally, we found climate warming and associated algal blooms boosted the long-term increase in the emissions via reconstructing historical (2003-2020) daily time series of CH4 emissions. This study demonstrates the great potential of satellites to map lake CH4 emissions by providing spatiotemporal continuous data, with new and timely insights into accurately understanding the magnitude of aquatic greenhouse gas emissions.

Large scale seasonal forecasting of peak season algae metrics in the Midwest and Northeast U.S.

In recent decades, many inland lakes have seen an increase in the prevalence of potentially harmful algae. In many inland lakes, the peak season for algae abundance (summer and early fall in the northern hemisphere) coincides with the peak season for recreational use. Currently, little information regarding expected algae conditions is available prior to the peak season for productivity in inland lakes. Peak season algae conditions are influenced by an array of pre-season (spring and early summer) local and global scale variables; identifying these variables for forecast development may be useful in managing potential public health threats posed by harmful algae. Using the LAGOS-NE dataset, pre-season local and global drivers of peak-season algae metrics (represented by chlorophyll-a) are identified for 178 lakes across the Northeast and Midwest U.S. from readily available gridded datasets. Forecasting models are built for each lake conditioned on relevant pre-season predictors. Forecasts are assessed for the magnitude, severity, and duration of seasonal chlorophyll concentrations. Regions of pre-season sea surface temperature, and pre-season chlorophyll-a demonstrate the most predictive power for peak season algae metrics, and resulting models show significant skill. Based on categorical forecast metrics, more than 70% of magnitude models and 90% of duration models outperform climatology.  Forecasts of high and severe algae magnitude perform best in large mesotrophic and oligotrophic lakes, however, high algae duration performance appears less dependent on lake characteristics. The advance notice of elevated algae biomass provided by these models may allow lake managers to better prepare for challenges posed by algae during the high use season for inland lakes.

Inversion and distribution of total suspended matter in water based on remote sensing images-A case study on Yuqiao Reservoir, China.

In this paper, Yuqiao Reservoir is taken as the research object. The total suspended matter (TSM) produced by the economic development in the upper reaches of the reservoir and its surrounding areas has brought great ecological harm to the safe operation of the reservoir. Satellite remote sensing technology provides a good way to obtain the temporal and spatial variation of TSM in the study area. Two field surveys were carried out in the Yuqiao Reservoir, a total of 44 sampling points collected in the two tests. The spectral data and concentration of TSM were obtained. We developed and validated a robust empirical model to estimate the concentration of TSM in the water of the Yuqiao Reservoir for the first time. The TSM distribution map of the Yuqiao Reservoir in 2013-2018 is retrieved based on Landsat 8 OLI images. This paper analyzes the spatial distribution characteristics of TSM concentration in the Yuqiao Reservoir for several years, as well as the interannual, seasonal, and monthly variation laws and development trends. The results show that the spatial distribution of TSM in Yuqiao Reservoir shows a decreasing trend from the periphery to the center; the interannual changes are mainly as follows: The annual change trend of TSM in Yuqiao Reservoir is not obvious; the seasonal changes are significant: the highest in summer (higher than 40 mg/L), the second in autumn, and the lowest in spring and winter (lower than 15 mg/L); and the monthly changes show regular fluctuations: In a year cycle, the concentration of TSM generally shows an inverted V-shaped trend; that is, TSM increases gradually from January to August and decreases gradually from August to December. The research results of this paper can be applied to other similar types of land water bodies, which will promote the wide application of Landsat 8 OLI images in the monitoring of TSM in lakes, rivers, and reservoirs in different regions across China, and provide data support for the scientific management of the safe operation of research areas. PRACTITIONER POINTS: The monitoring model of TSM in Yuqiao Reservoir was built for the first time. Temporal and spatial analysis of TSM concentration in Yuqiao Reservoir for the first time. The concentration of TSM is in Yuqiao Reservoir greatly affected by wind speed and precipitation.

Shrinking lakes, air pollution, and human health: Evidence from California's Salton Sea.

Due to increased water withdrawals and ongoing climate change, many inland lakes around the world are shrinking and dry lake beds can be significant sources of particulate matter air pollution. Using a natural experiment provided by the shrinking Salton Sea in California, this paper shows that each one-foot drop in lake elevation is associated with a 0.28 µg/m3 (2.6%) increase in PM2.5 concentrations. IV model results then show that Salton Sea-induced changes in PM2.5 over 1998-2014 led to increases in respiratory mortality of 1.4/yr.-15.6/yr. in the counties surrounding the lake, generating $13.2-$147.3 million in annual health costs.

First description of an euryoecious acanthoecid choanoflagellate species, Enibas tolerabilis gen. et sp. nov. from a salar in the Chilean Andes based on morphological and transcriptomic data.

In general, acanthoecid choanoflagellates have been described to occur exclusively in brackish water to marine habitats. Only recently, two studies have proven their existence in inland waters. One of them has shown, that an acanthoecid species from a small lake (near Apia on the island of Upolu, Samoa) is strictly freshwater adapted, not able to tolerate even brackish water. In this study, we present the first euryoecious acanthoecid species, able to live and reproduce in freshwater as well as under hypersaline conditions. The new species, Enibas tolerabilis gen. et sp. nov. was isolated in 2017 from the Salar de Ascotán in the Altiplano at 3750 m a. s. l., Northern Chile. The salinity at the time of sampling was 6 PSU. A series of autecological experiments have revealed a salinity tolerance from freshwater up to 70 PSU. In our phylogenetic analysis, E. tolerabilis gen. et sp. nov. clustered within the family of Acanthoecidae, forming a well-supported sister clade together with two other, environmental choanoflagellate sequences. We erected a new genus, Enibas gen. nov. and described the morphology, molecular biology and autecology for E. tolerabilis gen. et sp. nov. which has a stephanoecid-like lorica morphology. We emphasize that the definition of the genus Stephanoeca, being polyphyletic, is in urgent need of revision as we showed that this morphology is present in both acanthoecid families.

Quantifying multiple pressure interactions affecting populations of a recreationally and commercially important freshwater fish.

The expanding human global footprint and growing demand for freshwater have placed tremendous stress on inland aquatic ecosystems. Aichi Target 10 of the Convention on Biological Diversity aims to minimize anthropogenic pressures affecting vulnerable ecosystems, and pressure interactions are increasingly being incorporated into environmental management and climate change adaptation strategies. In this study, we explore how climate change, overfishing, forest disturbance, and invasive species pressures interact to affect inland lake walleye (Sander vitreus) populations. Walleye support subsistence, recreational, and commercial fisheries and are one of most sought-after freshwater fish species in North America. Using data from 444 lakes situated across an area of 475 000 km2 in Ontario, Canada, we apply a novel statistical tool, R-INLA, to determine how walleye biomass deficit (carrying capacity-observed biomass) is impacted by multiple pressures. Individually, angling activity and the presence of invasive zebra mussels (Dreissena polymorpha) were positively related to biomass deficits. In combination, zebra mussel presence interacted negatively and antagonistically with angling activity and percentage decrease in watershed mature forest cover. Velocity of climate change in growing degree days above 5°C and decrease in mature forest cover interacted to negatively affect walleye populations. Our study demonstrates how multiple pressure evaluations can be conducted for hundreds of populations to identify influential pressures and vulnerable ecosystems. Understanding pressure interactions is necessary to guide management and climate change adaptation strategies, and achieve global biodiversity targets.

Identification of the influence of distal inputs on mercury loading across the mid Great Lakes region using chemical sediment chronologies.

Sediment cores from 47 inland lakes in Michigan, USA were used to assess spatial and temporal trends in loadings of mercury (Hg). Focusing/background corrected accumulation rates and inventories and peak concentrations were used to examine: 1) responses of loadings to post-1990 reductions in emissions, 2) if spatial trends are consistent with modeled Hg deposition and 3) evidence for local and distal inputs. Results showed that decreases in concentrations and anthropogenic accumulation rates of Hg were consistent with recent reductions in emissions of Hg. Most lakes exhibiting a decreasing trend were located within an area with the most emission sources. Not all lakes showed the decreasing trend with some showing increases or no change. These lakes tended to be in the northern portion of the state. In all lakes, current concentrations of Hg remain greater than long-term, historical, background concentrations. Sub-regional mean inventories and mean decadal accumulation rates exhibited a south to north gradient, consistent with previously modeled spatial trends. However, individual lake inventories and rates of accumulation compared at shorter times scales varied among lakes. Evidence for event deposition (e.g., volcanic eruptions, manufacturing) was also variable among lakes. These results suggest influence of more distal inputs of Hg, perhaps driven by well-mixed, global sources. Cause(s) of variability on shorter time scales (e.g., events) needs further work. Finally, the results reveal that understanding risks to humans and ecosystems due to exposure to Hg and developing effective abatement policy is challenging.

Assessment of Chlorophyll-a Algorithms Considering Different Trophic Statuses and Optimal Bands.

Numerous algorithms have been proposed to retrieve chlorophyll-a concentrations in Case 2 waters; however, the retrieval accuracy is far from satisfactory. In this research, seven algorithms are assessed with different band combinations of multispectral and hyperspectral bands using linear (LN), quadratic polynomial (QP) and power (PW) regression approaches, resulting in altogether 43 algorithmic combinations. These algorithms are evaluated by using simulated and measured datasets to understand the strengths and limitations of these algorithms. Two simulated datasets comprising 500,000 reflectance spectra each, both based on wide ranges of inherent optical properties (IOPs), are generated for the calibration and validation stages. Results reveal that the regression approach (i.e., LN, QP, and PW) has more influence on the simulated dataset than on the measured one. The algorithms that incorporated linear regression provide the highest retrieval accuracy for the simulated dataset. Results from simulated datasets reveal that the 3-band (3b) algorithm that incorporate 665-nm and 680-nm bands and band tuning selection approach outperformed other algorithms with root mean square error (RMSE) of 15.87 mg·m-3, 16.25 mg·m-3, and 19.05 mg·m-3, respectively. The spatial distribution of the best performing algorithms, for various combinations of chlorophyll-a (Chla) and non-algal particles (NAP) concentrations, show that the 3b_tuning_QP and 3b_680_QP outperform other algorithms in terms of minimum RMSE frequency of 33.19% and 60.52%, respectively. However, the two algorithms failed to accurately retrieve Chla for many combinations of Chla and NAP, particularly for low Chla and NAP concentrations. In addition, the spatial distribution emphasizes that no single algorithm can provide outstanding accuracy for Chla retrieval and that multi-algorithms should be included to reduce the error. Comparing the results of the measured and simulated datasets reveal that the algorithms that incorporate the 665-nm band outperform other algorithms for measured dataset (RMSE = 36.84 mg·m-3), while algorithms that incorporate the band tuning approach provide the highest retrieval accuracy for the simulated dataset (RMSE = 25.05 mg·m-3).