Innovative approach for predicting daily reference evapotranspiration using improved shallow and deep learning models in a coastal region: A comparative study.

Accurate and reliable estimation of Reference Evapotranspiration (ETo) is crucial for water resources management, hydrological processes, and agricultural production. The FAO-56 Penman-Monteith (FAO-56PM) approach is recommended as the standard model for ETo estimation; nevertheless, the absence of comprehensive meteorological variables at many global locations frequently restricts its implementation. This study compares shallow learning (SL) and deep learning (DL) models for estimating daily ETo against the FAO-56PM approach based on various statistic metrics and graphic tool over a coastal Red Sea region, Sudan. A novel approach of the SL model, the Catboost Regressor (CBR) and three DL models: 1D-Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) were adopted and coupled with a semi-supervised pseudo-labeling (PL) technique. Six scenarios were developed regarding different input combinations of meteorological variables such as air temperature (Tmin, Tmax, and Tmean), wind speed (U2), relative humidity (RH), sunshine hours duration (SSH), net radiation (Rn), and saturation vapor pressure deficit (es-ea). The results showed that the PL technique reduced the systematic error of SL and DL models during training for all the scenarios. The input combination of Tmin, Tmax, Tmean, and RH reflected higher performance than other combinations for all employed models. The CBR-PL model demonstrated good generalization abilities to predict daily ETo and was the overall superior model in the testing phase according to prediction accuracy, stability analysis, and less computation cost compared to DL models. Thus, the relatively simple CBR-PL model is highly recommended as a promising tool for predicting daily ETo in coastal regions worldwide which have limited climate data.

Dataset comparing the growth of fodder crops and soil structure dynamics in an industrial biosludge amended arid soil.

The dataset in this work compares the response of two fodder crops, alfalfa (Medicago sativa) and buffel grass (Cenchrus ciliaris), to industrial biosludge amendment of an arid soil in the State of Qatar. It also evaluates the response of soil structure parameters in the biosludge-amended soils containing the different fodder crops. The dataset relates to our previously published works detailed subsequently. The underlying data comparing the water storage capacity and pore structure evolution of the planted soils treated with 0.75, 1.5, and 3% biosludge contents, which showed good outcomes in the companion articles, alongside soil only and soil-fertilizer controls, are presented. These are shown in terms of the percentage of irrigation water leached, and variations in the logarithmic mean T2 (i.e., T2LM - a proxy for mean pore size) and cumulative porosity, respectively. Data on plant growth parameters such as the number of days to flowering, plant height, and aboveground fresh biomass weight in individual replicates of the different treatments as a percentage of the soil-fertilizer control are also shown. The dataset shows the different responses of both plants and the planted soils to amendments with industrial biosludge from the wastewater treatment plant of a gas-to-liquid (GTL) plant.

Recycling industrial biosludge for buffel grass production in Qatar: Impact on soil, leachate and plant characteristics.

The agricultural industry in Qatar is highly dependent on using soil enhancing materials due to challenging soil and climatic conditions. Hence, this work investigated the potential of industrial biosludge from the wastewater treatment plant (WWTP) of a Gas-to-Liquids (GTL) plant to enhance an arid soil compared to fertilizer and compost. A fodder crop, buffel grass (Cenchrus ciliaris), was grown in semi-controlled pots containing a typical Qatari agricultural soil and admixtures over a 12-month period. The treatments included soil plus five biosludge percentage contents: 0.75, 1.5, 3, 6 and 12%. These were compared with soil only, soil plus 20-20-20 NPK fertilizer and soil plus 3% compost controls. Analyses of soil physical and chemical properties, the resulting leachate, and plant growth characteristics were conducted at set periods. The results indicate that up to 3% biosludge content led to better plant growth compared to the controls, with the optimum at 1.5% biosludge content for all growth characteristics studied. Biosludge addition to soil increased the volume of different pore types, especially micropores, which enhanced water retention and influenced plant growth. Regression modelling identified leachate Si and Fe concentrations, and biomass K content as the most influential variables for fresh biomass weight, plant height and the number of tillers, respectively. Biosludge addition to the soil around the optimum level did not cause detrimental changes to the resulting leachate and plant biomass. The findings of this work could lead to minimization of biosludge landfilling and allow for savings in fertilizers and irrigation water in arid regions.

Dataset on the influence of gas-to-liquid biosludge on arid soil properties and growth performance of alfalfa.

The dataset presented here is related to our research article entitled "Effect of gas-to-liquid biosludge on soil properties and alfalfa yields in an arid soil" [1]. It relates to selected performance parameters of alfalfa grown in an arid soil amended with five different (0.75-12%) gas-to-liquid biosludge contents, and selected properties of the soil determined using several material characterization techniques. A detailed description of the raw data relating to figures on alfalfa performance parameters such as fresh biomass weight, plant height, the number of tillers, and biomass elemental content in the companion article is provided alongside additional data on the number of days to flowering. The underlying data for leachate from the soil and underlying spectra and diffractograms for the proton nuclear magnetic resonance (1H-NMR) and X-ray diffraction (XRD) data, respectively, shown in the companion article are presented. These show changes in the pore structure characteristics and the mineralogical composition of the soil, soil-fertilizer, soil-biosludge, and soil-compost mixtures tested over time. Additional data showing the effect of the amendments on the bulk and particle densities of the soil is presented. The dataset demonstrates the influence of the industrial biosludge on arid soil properties and alfalfa yields (Kogbara et al., [1]).

Pattern of glomerular diseases in Sudanese children: a clinico-pathological study.

Glomerular diseases are a common cause of chronic kidney disease (CKD) in many countries. The pattern of glomerular diseases has been reported in adult Sudanese patients but there has been no previous study on Sudanese children. The aim of this study is to describe the pattern of glomerular diseases in Sudanese children from a clinico-pathological perspective. We retrospectively reviewed the clinical records of 321 children seen with nephritis/nephrosis at the Pediatric Nephrology Unit, Soba University Hospital and Dr. Salma Dialysis and Kidney Transplantation Centre, Khartoum, Sudan during the period from 2002 to 2007. Biopsies were studied with light microscopy and immuno-histochemistry with electron microscopy performed abroad in selected patients (predominantly Alport's). The mean age of the 321 study children was 8.71 years (range 2 months-16 yrs) of whom, 188 were males (60.2%). The most common presentation was with the nephrotic syndrome, seen in 202 patients (62.9%). The most common glomerular disease encountered was minimal change disease, seen in 96 children (29.9%), followed by post-infectious GN in 78 (24.3%) and focal and segmental glomerulosclerosis, seen in 44 patients (13.7%). Membranoproliferative GN (MPGN) was seen in 43 patients (13.4%) while mesangioproliferative GN was seen in 24 (7.5%). Systemic lupus erythematosus (SLE) was the most common secondary glomerular disease accounting for 16 patients (4.9%). HBsAg was positive in 10 patients and the most common associated lesion was MPGN (60%). Histopathology enabled us to change the therapy in 55.3% of the patients. Our study suggests that the pattern of GN in our cohort of patients is comparable with reports from other parts of the world with a high prevalence of post-infectious GN. Renal biopsies have an important part in planning therapy and management. Also, the importance of establishing a Sudanese renal registry including pediatric patients is stressed.

Highlights on the etiology of keloid.

The keloid phenomenon is old and perplexing. Many hypotheses were advanced to account for keloid growth but none of them provided a satisfactory explanation for the clinical manifestations of the disease. To solve the mystery of keloid detailed clinical studies coupled with laboratory tests were undertaken on keloid and non-keloid individuals; these highlighted the determinants of the disease and paved the way to the formulation of the Sebum Auto-immune Theory. The latter provided valid explanations for the clinical manifestations of the disease and indicated a rationale for new trends of management.