Mean Monthly Air Research Articles

Advanced Forecasting of Drought Zones in Canada Using Deep Learning and CMIP6 Projections

This study addresses the critical issue of drought zoning in Canada using advanced deep learning techniques. Drought, exacerbated by climate change, significantly affects ecosystems, agriculture, and water resources. Canadian Drought Monitor (CDM) data provided by the Canadian government and ERA5-Land daily data were utilized to generate a comprehensive time series of mean monthly precipitation and air temperature for 199 sample locations in Canada from 1979 to 2023. These data were processed in the Google Earth Engine (GEE) environment and used to develop a Convolutional Neural Network (CNN) model to estimate CDM values, thereby filling gaps in historical drought data. The CanESM5 climate model, as assessed in the IPCC Sixth Assessment Report, was employed under four climate change scenarios to predict future drought conditions. Our CNN model forecasts CDM values up to 2100, enabling accurate drought zoning. The results reveal significant trends in temperature changes, indicating areas most vulnerable to future droughts, while precipitation shows a slow increasing trend. Our analysis indicates that under extreme climate scenarios, certain regions may experience a significant increase in the frequency and severity of droughts, necessitating proactive planning and mitigation strategies. These findings are critical for policymakers and stakeholders in designing effective drought management and adaptation programs.

Evolution the Relationship Between Physiologically Equivalent Temperature and Some Meteorological Parameters for Basra City, Iraq

Background: Physiologically equivalent temperatures (PET) is highly efficient in evaluating the thermal component of any given microclimate as a single thermal index. The assist stakeholders in understanding and interpreting existing bioclimatic, allowing them to make any required modifications and become more robust to predicted climate change. Objective: This study assesses the relationship between Physiologically equivalent temperatures (PET) and some Meteorological Parameters. Methods: The data for this study includes observed mean monthly air temperature values, relative humidity, and wind speed for the period (2001-2020). The data was acquired from “Iraqi Meteorological Organization and Seismology (IMOS)” stations for Basra city. The radiation and Human Bioclimatic (RayMan) model were used to simulate bioclimatic indices (SET, UTCI, PET, PMV). Results: The findings revealed that the greatest mean values for PMV (4.3), SET (36.3), PET (45.5), and UTCI (42.1) were seen in July and August. The measurements have a nice thermal sensation of PMV (-0.5 - 1.9), SET (19.2- 29), PET (18.1- 31.8), and UTCI (15.9 - 28.7) is most noticeable in the months of (March, April, and October). The results showed the PET values (cool) and (Slightly cool) between (9- 18.3) for January, February, March, and December. The value of UTCI was between (5.9- 8.5) within classes (Slight cold stress), the values of PMV (-2.6- (-2.1)) within classes (strong cold stress) and (Slight cold stress) and the value of SET was (10.2- 12.4) within classes (Slight cold stress). Conclusions: Correlations between PET and air temperature (0.99), indicating good agreement between PET and air temperature, and relative humidity (0.96). PET and wind speed (R2=0.56). The scattering pattern of PET and other thermal indices shows that all indexes have a significant correlation coefficient, between PET and UTCI (R2=0.99), between PET and SET (R2=0.98), and (R2=0.99) between PET and PMV.

Анализ изменения сезонных явлений хвойных пород Лапландского заповедника и их связь с климатическими факторами.

The temperature regime for 29 years (1994–2022) at the weather station of Monchegorsk City is characterized. The average dates of onset of 9 phenological phases in pine (Pinus sylvestris L.) and spruce (Picea obovata Ledeb.)are given; for the period under consideration, significant trends were found only for several phenological phases of spruce. When comparing the dates of the phenophases "beginning of needle unfolding" for spruce and "beginning of flowering" for pine for the period from 2013 to 2022 with the dates of the period from 1964 to 1972, significant shifts towards earlier onset of these phenophases (by 10 and 8 days, respectively) were found. Correlations with mean monthly air temperatures were determined for nine phenophases for pine and spruce, and a high dependence of the onset of a number of phenological phases on temperatures in May for spruce and June for pine was revealed.

Spatiotemporal Evolution of the Land Cover over Deception Island, Antarctica, Its Driving Mechanisms, and Its Impact on the Shortwave Albedo

The aim of this work is to provide a full description of how air temperature and solar radiation induce changes in the land cover over an Antarctic site. We use shortwave broadband albedo (albedo integrated in the range 300–3000 nm) from a spaceborne sensor and from field surveys to calculate the monthly relative abundance of landscape units. Field albedo data were collected in January 2019 using a portable albedometer over seven landscape units: clean fresh snow; clean old snow; rugged landscape composed of dirty snow with disperse pyroclasts and rocky outcrops; dirty snow; stripes of bare soil and snow; shallow snow with small bare soil patches; and bare soil. The MODIS MCD43A3 daily albedo products were downloaded using the Google Earth Engine API from the 2000–2001 season to the 2020–2021 season. Each landscape unit was characterized by an albedo normal distribution. The monthly relative abundances of the landscape units were calculated by fitting a linear combination of the normal distributions to a histogram of the MODIS monthly mean albedo. The monthly relative abundance of the landscape unit consisting of rugged landscape composed of dirty snow with dispersed clasts and small rocky outcrops exhibits a high positive linear correlation with the monthly mean albedo (R2 = 0.87) and a high negative linear correlation with the monthly mean air temperature (R2 = 0.69). The increase in the solar radiation energy flux from September to December coincides with the decrease in the relative abundance of the landscape unit composed of dirty snow with dispersed clasts and small rocky outcrops. We propose a mechanism to describe the evolution of the landscape: uncovered pyroclasts act as melting centers favoring the melting of surrounding snow. Ash does not play a decisive role in the melting of the snow. The results also explain the observed decrease in the thaw depth of the permafrost on the island in the period 2006–2014, resulting from an increase in the snow cover over the whole island.

Monthly stream temperatures along the Danube River: Statistical analysis and predictive modelling with incremental climate change scenarios

Abstract The aim of the study is to analyse changes and predict the course of mean monthly water temperatures of the Danube River at various locations for the future. The first part of the study involves conducting a statistical analysis of the annual and monthly average air temperatures, water temperatures, and discharges along the Danube River. The study examines long-term trends, changes in the trends, and multiannual variability in the time series. The second part of the study focuses on simulating the average monthly water temperatures using Seasonal Autoregressive Integrated Moving Average (SARIMA) models and nonlinear regression models (NonL), based on two RCP based incremental mean monthly air temperature scenarios. To assess the impact of future climate on stream temperatures, the historical long-term average of the monthly water temperature (1990–2020) was compared with scenarios S1 (2041–2070) and S2 (2071–2100). The simulation results from the two stochastic models, the SARIMA and NonL, showed that in scenario S1, the Danube River’s average monthly water temperature is projected to increase by 0.81/0.82°C (Passau), 0.55/0.71°C (Bratislava), and 0.68/0.56°C (Reni). In scenario S2, the models predict higher increases: 2.83/2.50°C (Passau), 2.06/2.46°C (Bratislava), and 2.52/1.90°C (Reni). Overall, the SARIMA model proved to be more stable and effective in simulating the increase in monthly water temperatures in the Danube River.

Spatial and Temporal Variability in Stream Thermal Regime Drivers for Three River Networks During the Summer Growing Season.

Many cold-water dependent aquatic organisms are experiencing habitat and population declines from increasing water temperatures. Identifying mechanisms which drive local and regional stream thermal regimes facilitates restoration at ecologically relevant scales. Stream temperatures vary spatially and temporally both within and among river basins. We developed a modeling process to identify statistical relationships between drivers of stream temperature and covariates representing landscape, climate, and management-related processes. The modeling process was tested in 3 study areas of the Pacific Northwest USA during the growing season (May [start], August [warmest], September [end]). Across all months and study systems, covariates with the highest relative importance represented the physical landscape (elevation [1st], catchment area [3rd], main channel slope [5th]) and climate covariates (mean monthly air temperature [2nd] and discharge [4th]). Two management covariates (ground water use [6th] and riparian shade [7th]) also had high relative importance. Across the growing season (for all basins) local reach slope had high relative importance in May, but transitioned to a regional main channel slope covariate in August and September. This modeling process identified regionally similar and locally unique relationships among drivers of stream temperature. High relative importance of management-related covariates suggested potential restoration actions for each system.

Climate and Weather Condition of Balochistan Province, Pakistan

The study discusses the climate of Balochistan with a special focus on the variation of weather condition taking into account the mean monthly precipitation, temperature, humidity, atmospheric circulation, air pressure, evapotranspiration and solar energy covering the time duration of 1931-2020 (normal data). The physical barriers that bring variations in the climate of Balochistan contain geographical location, ocean, geomorphology, land use, natural vegetation, and continental extent. Based on precipitation, the province has been divided into two main regions that are arid and semi-arid, while the temperature zones are hot, warm, mild and cool. The southern and eastern part of the province receives heavy rain in the summers (monsoon), whereas it is from the western depressions during the winter season. Balochistan experiences four rainy seasons in winter (cold), pre-monsoon season (warm), monsoon season (hot), and post-monsoon season (mild). Owing to tropical (coastal) and sub-tropical continental characteristics, the area familiarizes two foremost seasons namely winter and summer. The summers of the area long for 5 months in hilly areas while 7 months in continental plains and coastal regions; whereas, winters cover five months in the plains and seven months in the mountains. Based on the appropriation and fluctuation in climate constituents, Balochistan has been classified into two main, 6 meso, and 9 microclimate and weather zones. According to Global Climate Risk Index, 2021, Pakistan has been ranked at 8th in the list of top ten global climate high-risk countries, which are exposed to the ongoing climate change and requires attention to resolve the issue.

Assessment of Temperature, Precipitation, and Snow Cover at Different Altitudes of the Varzob River Basin in Tajikistan

The analysis of precipitation, snow cover, and temperature based on measured data is important for many applications in hydrology, meteorology, climatology, disaster management, and human activities. In this study, we used long-term historical datasets from the Varzob River Basin (VRB) in Tajikistan to evaluate the trend and magnitudinal changes in temperature, precipitation, and snow cover area in the Anzob (upstream), Maykhura (midstream), and Hushyori (downstream) regions of the VRB using the original Mann–Kendall test, modified Mann–Kendall test, Sen’s slope test, and Pettitt test. The results revealed a decreasing trend in the mean monthly air temperature at Anzob station in the upstream region for all months except January, February, and December between 1960 and 2018 and 1991 to 2018. In each of the three regions, the mean annual temperature indicated a clear upward trend. Seasonal precipitation indicated a large increasing trend in January and February at the Anzob station from 1960 to 2018, but a significant downward trend in April in the upstream, midstream, and downstream regions between 1960 and 1990 and from 1991 to and 2018. In the VRB, almost all stations exhibited a downward trend in annual precipitation across all periods, whereas the upstream region showed a non-significant upward trend between 1960 and 1990. The monthly analysis of snow cover in the VRB based on ground data showed that the maximum increase in snow cover occurs in April at the Anzob station (178 cm) and in March at Maykhura (138 cm) and Hushyori stations (54 cm). The Mann–Kendall test, based on MODIS data, revealed that the monthly snow cover in the VRB increased in April and July while a decrease was recorded in February, September, November, and December from 2001 to 2022. The trend’s stable pattern was observed in March, May, August, and October.

Age matters: Older Alnus viridis ssp. fruticosa are more sensitive to summer temperatures in the Alaskan Arctic

Abstract The Arctic is rapidly warming, and tundra vegetation community composition is changing from small, prostrate shrubs to taller, erect shrubs in some locations. Across much of the Arctic, the sensitivity of shrub secondary growth, as measured by growth ring width, to climate has changed with increased warming, but it is not fully understood how shrub age contributes to shifts in climate sensitivity. We studied Siberian alder, Alnus viridis ssp. fruticosa, a large nitrogen‐fixing shrub that has responded to climate warming with northward range expansion over the last 50 years. We used serial sectioning of 26 individual shrubs and 94 cross‐sections to generate a 98‐year growth ring chronology, including one 142‐year‐old, Siberian alder in Northern Alaska. We tested how secondary growth sensitivity to climate has changed over the past century (1920–2017) and how shrub age affects climate sensitivity of alder growth through time. We found that over time, alder growth as expressed by the stand chronology became more sensitive to July mean monthly air temperature. Older shrubs displayed higher sensitivity to June and July temperature than younger alders. However, during the first 30 years of growth of any shrub, temperature sensitivity did not differ among individuals. In addition, the June temperature sensitivity of growth series from individual cross‐sections depended on the age of the attached shrub. Our results suggest that age contributes to climate sensitivity, likely through modifying internal shrub carbon budgets by changing size and reducing alder's dependence on N‐fixation over time. Older, more sensitive alder may enhance C and N‐cycling while having greater recruitment potential. Linking alder age to climate sensitivity, recruitment and total N‐inputs will enable us to better predict ecosystem carbon and nitrogen cycling in a warmer Arctic. Read the free Plain Language Summary for this article on the Journal blog.

Assessment of Land Surface Schemes from the WRF-Chem for Atmospheric Modeling in the Andean Region of Ecuador

Surface interactions occur near the land–atmosphere interface, thus affecting the temperature, convection, boundary layer, and stability of the atmosphere. A proper representation of surface interactions is a crucial component for numerical atmospheric and air quality modeling. We assessed four land surface schemes—1. 5–layer thermal diffusion scheme (1 5-Layer); 2. unified Noah land surface model (2 Noah); 3. rapid update cycle (3 RUC) land surface model; and 4. Pleim–Xiu land surface model (4 Pleim–Xiu)—from the Weather Research and Forecasting with Chemistry (WRF-Chem V3.2) model for the purposes of atmospheric modeling in Cuenca, which is a region with a complex topography and land use configuration and which is located in the Southern Andean region, in Ecuador. For this purpose, we modeled the meteorological and air quality variables during September 2014. It was found that the meteorological and short-term air quality variables were better modeled through the 2 Noah scheme. Long-term (mean monthly) air quality variables were better modeled by the 1 5–Layer and 3 RUC options. On average, the 2 Noah scheme was better at modeling meteorology and air quality. In addition, we assessed the 2 Noah scheme combined with the urban canopy model (UCM) (5 Noah UCM), which was developed as an option to represent the urban effects at a subgrid-scale. Results indicated that the performance of the 5 Noah UCM scheme was not better at modeling than the 2 Noah scheme alone. Moreover, the 5 Noah UCM scheme notably decreased the modeling performance for carbon monoxide and fine particulate matter. These results complement previous assessments of other schemes, allowing us to recommend a basic configuration of parameters for atmospheric modeling in the Andean region of Ecuador.

Convenient Sampling of Xylem Sap from Adult Tree Trunks and Analysis of Its Components

Sampling xylem sap, especially from adult tree trunks, is a major challenge. In this study, we developed a new sampling method and tested its efficacy for sampling xylem sap from deciduous Quercus serrata and evergreen Cryptomeria japonica. The water-absorbing resin was placed in cylindrical holes in the tree trunks, and the xylem sap that was collected in the resin was analyzed for 15 metals, 4 nonmetals, total sugars, and the chemical forms of nitrogen, phosphorus, and sulfur. The volume of the collected xylem sap increased with increases in the mean monthly air temperature and the monthly precipitation when it was less than ca. 200 mm. The concentrations of sap components were higher in Q. serrata than in C. japonica. In Q. serrata, the concentrations of most sap components (e.g., K) began to increase in early spring, remained high in spring–summer, decreased in late summer–early autumn, and remained low in winter. This seasonal variation was likely associated with tree phenology. Relationships between the concentrations of elements in the sap and those in the leaves and soil solution were observed. This sampling method is appropriate for characterizing weekly and monthly mean concentrations of xylem sap components.

Proposal of a new method for drought analysis

Abstract Below-average precipitation and above-average air temperature are important factors in the occurrence and intensity of drought. In the context of global climate change, air temperature increase, as a key climatological parameter, has to be considered when calculating the drought index. We introduce a new method of drought analysis, relying on standardized values of precipitation and mean air temperatures for a certain period. The standardized value is calculated by subtracting the average value for each period from each measured value and dividing the obtained value by the standard deviation of the sample. Next, the New Drought Index (NDI) is calculated by subtracting the standardized temperature value from the standardized precipitation value. NDI values were determined for the monthly and annual precipitation time series and mean monthly and annual air temperatures measured at the stations Split-Marjan and Zagreb-Grič between 1948 and 2020. The NDI indicates that the risk of drought has intensified significantly in recent decades, which may be related to the effect of global warming.

Climate change impacts the state of winter roads connecting indigenous communities: Case study of Sakha (Yakutia) Republic

Winter roads, or zimnik, serve as major connections between communities across the global Arctic, including Sakha (Yakutia) Republic. Although accessible to general public, winter roads in remote regions are primarily used by indigenous communities. Sustainability of winter roads is reduced by climate change effects, via shorter and milder winters, extended shoulder seasons, delayed freeze up and advanced ice break up on rivers used as ice roads. We review the observed and projected change in mean monthly air temperatures, MMAT, °C, during cold season in six localities of the Sakha (Yakutia) Republic, important residence areas of the indigenous peoples of the North. In observed MMAT records, only North-Western Yakutia hasn’t experienced significant warming. In other localities, a significant step-shift change is observed in months from March to June, and at several stations, also in October and November. Under future climate, assessed with a regional ensemble of global climate models, projected change is expected in core winter months, November to February. In the near future, 2021–2050 period, increase in MMAT is expected mostly in December and January, with only minor increase in shoulder seasons, except in southern Yakutia. In the far future, 2071–2100, only under optimistic SSP 1–2.6 scenario the MMAT change is contained within +3.5 °C, and even in this case, April MMAT increases above −2°C at stations in southern Yakutia. Under SSP 5–8.5 scenario, highest MMAT increase, up to over +12 °C, is projected in the Yakutian Arctic from December to February. In southern Yakutia, both October and April MMAT around or above 0 °C are projected. Winter Road Sustainability Index is assessed based on observed and projected climate. Over northern Yakutia, higher MMAT in core winter months suggest reduced ice thickness on rivers, but overall climate severity allows sustainable winter road operations throughout the season even under high emission scenarios. In the near future, only winter road operations around Tyanya, in the Evenki residence area, become moderately affected under most SSP scenarios. In the far future, winter road operations around Tyanya, Ust-Maya and Neryungri, also Evenki residence area, become highly vulnerable under most scenarios. Practical implications include institutional response, transport system adaptation, adjustment of road maintenance protocols, and reconsidering local production.

Assessment of tourist climate comfort on the example of Novi Sad

Climate elements are one of the most important factors for tourism development. This study aims to show the values of the tourist climate comfort index based on monthly values. For the needs of the research, the method of tourist climate comfort (TCCI) was used, on the example of the city of Novi Sad. Meteorological data for the climatological period of 30 years (1991-2020) from the meteorological station Rimski Sancevi were analysed. Meteorological data that were observed, analysed, and statistically processed are: mean monthly air temperature, monthly temperature amplitude, mean monthly humidity, monthly insolation, and number of rainy days. The obtained results indicate that May and September are the most climatologically suitable months for tourist activities. Data on the number of tourist arrivals and their overnight stays in this area covers the period from 2004-2020. In this paper, a linear correlation between the value of climate comfort and the number of tourists has been made in order to provide local authorities and tourism organizations a more precise overview of the perception and valorisation of climate elements for the improvement of tourist potential.

Modeling and forecasting air temperature in Tetouan (Morocco) using SARIMA model

Abstract The past decades have seen a growing concern to understand the impact of climate change at global and regional levels. In particular, air temperature has been considered as a key factor in climate impact studies on agricultural, ecological, environmental and economic sectors. In this study, a seasonal ARIMA model is developed through the use of the Box and Jenkins method (1970) to predict the long-term air temperature in the city of Tetouan. Indeed, over the period of 1980 to 2022 from Sania Ramel station of the city of Tetouan, the monthly mean air temperature data are used to build and verify the model. Four basic chronological steps, namely: Identification, Estimation, Validation and Prediction are established during the model development. The validity of the model is tested using the standardized residuals plots given by Box and Jenkins. After carrying out the necessary checks, the ARIMA (1,0,0)(1,1,0)[12] model proved to be the most effective for predicting future air temperature. Keywords: Air temperature, Time Series Forecasting, Box and Jenkins, Seasonal ARIMA.

Estimation of tendencies, homogeneity and stationarity of air temperature at the Ukrainian Antarctic Akademik Vernadsky station during 1951—2020

In this paper results of the complex analysis of surface air temperature tendencies investigations at the Ukrainian Antarctic Akademik Vernadsky station are represented. Antarctica is a region that has a high rate of surface air temperature increase. The Antarctic Peninsula has experienced particularly fast warming, which has the highest temperature rise in the Southern Hemisphere. Therefore, in Antarctica, the study of surface air temperature change is important.
 The Ukrainian Antarctic Akademik Vernadsky station is located on Galindez Island near the Antarctic Peninsula. Investigation of the surface air temperature is especially relevant to the Akademik Vernadsky station, because it has difficult conditions for its formation. The research goal is the estimation of tendencies, homogeneity and stationarity of the annual and mean monthly values of surface air temperature at the Ukrainian Antarctic Akademik Vernadsky station based on a combined approach with the use of several statistical and graphical methods. The use of various statistical methods that differ in characteristics (sensitivity to the law of distribution, autocorrelation, etc.) allows obtaining more reliable estimates. Graphic methods give an opportunity to analyze the tendencies over time and its change periods, the cyclical fluctuations and their characteristics (phases of increase and decrease, their duration, synchronicity, in-phase). Therefore, 4 statistical tests (standard normal Alexandersson test, Buishand test, Pettitt test, von Neumann relation) and 2 graphical methods (mass curve and residual mass curve) were used in the study.
 At the Ukrainian Antarctic Akademik Vernadsky station, the observation series of the mean annual air temperature are quasi-homogeneous and quasi-stationary, as it has only a cooling phase and a warming phase of long-term cyclical fluctuations, which are also unfinished. The transition from the cooling phase to the warming phase took place in 1982. Tendencies in mean monthly air temperatures are similar to tendencies in mean annual temperatures. The differences are only for some months, namely, for the period from September to December.

Historical and long-term climate trends in warm permafrost regions: A case study of Bethel, AK

Permafrost is very sensitive to climate factors, with warm permafrost particularly vulnerable to climate change. This paper aims to provide a detailed case study of climate trends of a high-latitude Alaskan site underlain by warm permafrost based on historical data and predictions from the Coupled Model Intercomparison Project Phase 5 (CMIP5). The climate data, including air temperature, precipitation, wind speed, and their annual and seasonal trends from 1950 to 2099, are presented for Bethel, Alaska. The downscaled data are compared with the historical data in the overlap period. Both air and design freezing and thawing indices are calculated using various methods. In comparison, the downscaled model predictions align well with air temperature and wind speed records but not for precipitation, indicating the need for further downscaling at a finer resolution. The historical annual temperature records show a warming rate of 0.40 °C per decade, which is predicted to almost double to 0.78 °C per decade in the 21st century, leading to shorter winters and longer summers. The historical annual precipitation increased by a rate of 14.8 mm per decade from 1950 to 2020, and this trend is predicted to continue but at a slightly lower rate. The wind speed decreased consistently from 1984 to 2020 by 0.9 km/h per decade. However, the CMIP5 predicts that such a trend will diminish, with the mean annual wind speed remaining almost unchanged in this century. The air freezing index exhibits a consistent downtrend from 1950 to 2020, whereas the air thawing index remained flat until 1980 and rose afterward; the CMIP5 predicts that both trends will continue in the 21st century. The design air freezing and thawing indices are sensitive to the assessment periods for both methods. An assessment period shorter than 30 years, e.g., ten years, is recommended to find design indices. It is conservative to use the monthly mean air temperature method for evaluating the design air freezing index and apply the extreme event method for the design thawing index.

Groundwater level prediction with meteorologically sensitive Gated Recurrent Unit (GRU) neural networks

Precise estimation of groundwater level (GWL) fluctuations has a substantial effect on water resources management. In the present study, to forecast the regional mean monthly time series groundwater level (GWL) with a range of 4.82 (m) in Urmia plain, three different layer structures of Gated Recurrent Unit (GRU) deep learning-based neural network models via the module of sequence-to-sequence regression are designed. In this sense, 180-time series datasets of regional mean monthly meteorological, hydrological, and observed water table depths of 42 different monitoring piezometers during the period of Oct 2002–Sep 2017 are employed as the input variables. By using Shannon entropy method, the most influential parameters on GWL are determined as regional mean monthly air temperature (Tam), precipitation (Pm), total (sum) water diversion discharge (Wdm) of four main rivers. Nevertheless, Cosine amplitude sensitivity analysis confirmed Tam as a dominant factor. For preventing overfitting problem, an algorithm tuning technique via different kinds of hyperparameters is operated. In this respect, several scenarios are implemented and the optimal hyperparameters are accomplished via the trial-and-error process. As stated by the performance evaluation metrics, Model Grading process, and Total Learnable Parameters (TLP) value, the innovative and unique suggested model (3), entitled GRU2+, (Double-GRU model coupled with Addition layer (+)) with seven layers is carefully chosen as the best model. The unique suggested model (3) in the optimal hyperparameters, resulted in an R2 of 0.91, a total grade (TG) of 7.76, an RMSE of 0.094 (m), and a running time of 47 (s). Thus, the model (3) can be certainly employed as an effective model to forecast GWL in different agricultural areas.

GPRChinaTemp1km: a high-resolution monthly air temperature data set for China (1951–2020) based on machine learning

Abstract. An accurate spatially continuous air temperature data set is crucial for multiple applications in the environmental and ecological sciences. Existing spatial interpolation methods have relatively low accuracy, and the resolution of available long-term gridded products of air temperature for China is coarse. Point observations from meteorological stations can provide long-term air temperature data series but cannot represent spatially continuous information. Here, we devised a method for spatial interpolation of air temperature data from meteorological stations based on powerful machine learning tools. First, to determine the optimal method for interpolation of air temperature data, we employed three machine learning models: random forest, support vector machine, and Gaussian process regression. A comparison of the mean absolute error, root mean square error, coefficient of determination, and residuals revealed that a Gaussian process regression had high accuracy and clearly outperformed the other two models regarding the interpolation of monthly maximum, minimum, and mean air temperatures. The machine learning methods were compared with three traditional methods used frequently for spatial interpolation: inverse distance weighting, ordinary kriging, and ANUSPLIN (Australian National University Spline). Results showed that the Gaussian process regression model had higher accuracy and greater robustness than the traditional methods regarding interpolation of monthly maximum, minimum, and mean air temperatures in each month. A comparison with the TerraClimate (Monthly Climate and Climatic Water Balance for Global Terrestrial Surfaces), FLDAS (Famine Early Warning Systems Network (FEWS NET) Land Data Assimilation System), and ERA5 (ECMWF, European Centre for Medium-Range Weather Forecasts, Climate Reanalysis) data sets revealed that the accuracy of the temperature data generated using the Gaussian process regression model was higher. Finally, using the Gaussian process regression method, we produced a long-term (January 1951 to December 2020) gridded monthly air temperature data set, with 1 km resolution and high accuracy for China, which we named GPRChinaTemp1km. The data set consists of three variables: monthly mean air temperature, monthly maximum air temperature, and monthly minimum air temperature. The obtained GPRChinaTemp1km data were used to analyse the spatiotemporal variations of air temperature using Theil–Sen median trend analysis in combination with the Mann–Kendall test. It was found that the monthly mean and minimum air temperatures across China were characterised by a significant trend of increase in each month, whereas monthly maximum air temperatures showed a more spatially heterogeneous pattern, with significant increase, non-significant increase, and non-significant decrease. The GPRChinaTemp1km data set is publicly available at https://doi.org/10.5281/zenodo.5112122 (He et al., 2021a) for monthly maximum air temperature, at https://doi.org/10.5281/zenodo.5111989 (He et al., 2021b) for monthly mean air temperature, and at https://doi.org/10.5281/zenodo.5112232 (He et al., 2021c) for monthly minimum air temperature.

A terrestrial record of climate variation during MIS 11 through multiproxy palaeotemperature reconstructions from Hoxne, UK

AbstractA terrestrial (lacustrine and fluvial) palaeoclimate record from Hoxne (Suffolk, UK) shows two temperate phases separated by a cold episode, correlated with MIS 11 subdivisions corresponding to isotopic events 11.3 (Hoxnian interglacial period), 11.24 (Stratum C cold interval), and 11.23 (warm interval with evidence of human presence). A robust, reproducible multiproxy consensus approach validates and combines quantitative palaeotemperature reconstructions from three invertebrate groups (beetles, chironomids, and ostracods) and plant indicator taxa with qualitative implications of molluscs and small vertebrates. Compared with the present, interglacial mean monthly air temperatures were similar or up to 4.0°C higher in summer, but similar or as much as 3.0°C lower in winter; the Stratum C cold interval, following prolonged nondeposition or erosion of the lake bed, experienced summers 2.5°C cooler and winters between 5°C and 10°C cooler than at present. Possible reworking of fossils into Stratum C from underlying interglacial assemblages is taken into account. Oxygen and carbon isotopes from ostracod shells indicate evaporatively enriched lake water during Stratum C deposition. Comparative evaluation shows that proxy-based palaeoclimate reconstruction methods are best tested against each other and, if validated, can be used to generate more refined and robust results through multiproxy consensus.