Assessment of drought conditions and prediction by machine learning algorithms using Standardized Precipitation Index and Standardized Water-Level Index (case study: Yazd province, Iran).

Drought as a natural phenomenon has always been a serious threat to regions with hot and dry climates. One of the major effects of drought is the drop in groundwater level. This paper focused on the SPI (Standardized Precipitation Index) and SWI (Standardized Water-Level Index) to assess meteorological and hydrological drought, respectively. In the first part, we used different time frames of SPI (3, 6, 12, and 24 months) to investigate drought in Yazd, a dry province in the center of Iran for 29 years (1990-2018). Then, in the second part, the relationship between SPI and SWI was investigated in the three aquifers of Yazd by some rain gauge stations and the closest observation wells to them. In addition to using SPI and SWI, we also used different machine learning (ML) algorithms to predict drought conditions including linear model and six non-linear models of K_Nearest_Neighbors, Gradient_Boosting, Decision_Tree, XGBoost, Random_Forest, and Neural_Net. To evaluate the accuracy of the mentioned models, three statistical indicators including Score, RMSE, and MAE were used. Based on the results of the first part, Yazd province has changed from mild wet to mild drought in terms of meteorological drought (the amount of rainfall according to SPI), and this condition can worsen due to climate change. The models used in ML showed that SPI-6 (score ave = 0.977), SPI-3 (score ave = 0.936), SPI-24 (score ave = 0.571), and SPI-12 (score ave = 0.413) indices had the highest accuracy, respectively. The models of Neural_Net (score ave = 0.964-RMSE ave = 0.020-MAE ave = 0.077) and Gradient_Boosting (score ave = 0.551-RMSE ave = 0.124-MAE ave = 0.248) had the highest and lowest accuracy in prediction of the SPI in all four-time scales. Based on the results of the second part, about the SWI, Random_Forest model (score = 0.929-RMSE = 0.052-MAE = 0.150) and model of Neural_Net (score = 0.755-RMSE = 0.235-MAE = 0.456) had the highest and lowest accuracy, respectively. Also, hydrological drought (reduction of the groundwater level) of the region has been much more severe, and according to the low correlation coefficient of average SPI and SWI (R2 = 0.14), we found that the uncontrolled pumping wells, as a main factor than a shortage of rainfall, have aggravated the hydrological drought, and this region is at risk of becoming a more arid region in the future.

Numerical modeling of groundwater flow and nitrate transport using MODFLOW and MT3DMS in the Karaj alluvial aquifer, Iran.

Nitrate is one of the most dangerous pollutants in groundwater, being regarded as a severe environmental hazard and a global-scale problem. The present study aims to analyze the groundwater flow and nitrate contamination in the Karaj unconfined aquifer, Central Iran. Simulation of the quantitative and qualitative status was performed using MODFLOW and MT3DMS. Sampling was done to model groundwater flow for eight seasonal time periods and nitrate pollution transport for four time periods (a total of 420 days), and calibration was carried out by trial-and-error method. Due to the predominance of advection term in the transport of nitrate pollution, the total variation diminishing method was used in transport modeling. The groundwater flow modeling showed a reservoir deficit of - 33 MCUM and 67 cm decrease in the water year 2016-2017 and 173 cm in the entire modeling period (2016-2018) in groundwater level. Also, the RMSE in the calibration and validation stages was obtained from 24.9 to 0.72 and 0.84, respectively. The nitrate contamination transport modeling indicated that there are three nitrate contamination concentration parts with more than safe concentration of nitrate (50 mg/l). The most pollution is in the urban areas in the east of the aquifer. The nitrate pollution is primarily anthropogenic due to industrial and especially domestic wastewater and then fertilizers used in agricultural activities. It can be predicted that with the full implementation of a municipal wastewater collection network, the nitrate pollution concentration in urban areas would reduce significantly to the range of 20 to 25 mg/l.

Prevalence of Pulmonary Hypertension in Patients with Thalassemia Intermedia in 2009: a single center's experience.

BACKGROUND: There are various clinical symptoms of thalassemia intermedia, and they lie roughly between those of major and minor forms of the disease. Patients with thalassemia intermedia occasionally require blood transfusions. This renders them susceptible to pulmonary arterial hypertension (PAH) syndrome, which is one of the most significant complications in patients with thalassemia intermedia. PAH is more common in in thalassemia intermedia than in thalassemia major, and it may cause cardiac complications in patients who are older than 30. The objective of this study was to estimate the prevalence of PAH in thalassemia intermedia patients so that they can be referred expeditiously for treatment, thereby preventing the complications that occur later. METHODS: This cross sectional study was conducted under the supervision of hematology department of Mashhad Medical University. Forty-one patients with thalassemia intermedia were examined at the Sarvar Thalassemia and Hemophilia Clinic of Mashhad. Electrocardiography, chest radiography, and echocardiography tests were performed for all of the patients by the same pediatric cardiologist. The data were processed by SPSS software, version 11.5, and the results were analyzed using chi-squared, Student's t, and Mann-Whitney tests. RESULTS: The mean age of the patients was 21.93±8.34. They had been under pediatric heart specialists' constant examination and treatment since their childhood when they were diagnosed with TI, and continue to receive regular follow-up care. The prevalence of pulmonary hypertension was 24% in our study population. In patients with thalassemia intermedia, the left ventricular (LV) mass indices were about 3-5 times higher than would be expected in a normal population. Patients with higher LV mass indices have a greater risk of developing pulmonary hypertension, and those with serum ferritin levels below 1000 ng/ml are less susceptible to diastolic dysfunction. CONCLUSION: Pulmonary hypertension is common in patients with thalassemia intermedia. Irregular chelation therapy or absence of this treatment might lead to diastolic dysfunction, and serum ferritin levels below 1000 ng/ml could be an important factor in preventing the development of diastolic dysfunction or slowing down its progression.