Multiple step ahead river flow modelling for south east tasmanian aquaculture

We develop multiple step ahead prediction models of river flow for locations in Tasmania (Australia) for decision support in aquaculture. In predicting river flows for multiple days ahead, we first statistically determine the maximum input lags of rainfall and river flow. We then use machine learning techniques in building models. In multiple step ahead prediction, we consider both static and dynamic approaches. In dynamic approach, one day prediction is served as input to two days ahead prediction. The experimental results demonstrate that, in general, a dynamic approach provides better accuracy in multiple day’s ahead prediction. For Duck Bay location using dynamic approach, support vector regression performs best over linear regression, M5P and multilayer perceptron. However, at Montagu Bay location, we find that M5P performs best over methods. We find that multiple step ahead prediction of river flow for each location requires modelling of lags with associated machine learning techniques.     

Geochemical evaluation and thermal modeling of the Eocene–Oligocene Pabdeh and Middle Cretaceous Gurpi Formations in the northern part of the Dezful Embayment

Rock–Eval pyrolysis analysis, burial history, and 1D thermal maturity modeling have allowed the evaluation of the source rock potential, thermal maturation state, and impacts of the Pabdeh and Gurpi Formations in Cretaceous–Miocene petroleum system in the Naft Safid (NS) and Zeloi (ZE) oilfields, North Dezful Embayment. The total organic carbon (TOC) content of the Pabdeh and Gurpi Formations ranges from 0.2 to 4.7 wt% and 0.3 to 5.3 wt%, respectively. S2 values of the Pabdeh Formation in the ZE and NS oilfields vary from 0.41 to 13.77 and 0.29 to 14.5 mg HC (Hydrocarbon)/g rock, with an average value of 4.48 and 4.14 mg HC/g rock, respectively. These values for the Gurpi Formation in the ZE and NS oilfields range from 0.31 to 16.96 and 0.26 to 1.44 mg HC/g rock, with an average value of 8.54 and 2.43 mg HC/g rock, respectively. The S2 versus TOC diagram reveals a fair to good hydrocarbon generation potential of the Pabdeh Formation and poor to fair potential of the Gurpi Formation. The high values of S2 (S2 > S1) for samples of the both formations in the ZE and NS oilfields show that the samples are not contaminated with petroleum generated from underlying source rocks. The samples of the Pabdeh Formation in the ZE oilfield are characterized by a relatively narrow range of activation energy values with principal activation energy of 46 kcal/mol and frequency factor of 5.27 × 10⁺¹¹ s^?1. It seems that the high sulfur content of the Pabdeh organic matter probably caused the frequency factor and principal activation energy to be lower than usual. Hydrogen index (HI) values of the Pabdeh and Gurpi Formations in the ZE oilfield vary from 71 to 786 and 97 to 398 mg HC/g TOC, with an average value of 310 and 277 mg HC/g TOC, respectively. These values in the NS oilfield range from 66 to 546 and 51 to 525 mg HC/g TOC, with an average value of 256 and 227 mg HC/g TOC, respectively. Plot of HI vs. T _max value indicates that the majority of the Pabdeh and Gurpi samples contain predominantly type II kerogen and their organofacies are directly related to the more homogeneous precursor materials. Based on thermal maturity modeling results, kinetic parameters, and Rock–Eval analysis, both formations in the ZE and NS oilfields are thermally mature and immature or early mature stage, respectively.     

Petrophysical parameters and modelling of the Eocene reservoirs in the Qadirpur area,Central Indus Basin,Pakistan: implications from well log analysis

The Eocene rock units of the Qadirpur field, Central Indus Basin (Pakistan), are investigated petrophysically for their detailed reservoir characterization. The different petrophysical parameters determined include the following: true resistivity, shale volume, total porosity, effective porosity, density and neutron porosity, water and hydrocarbon saturation, bulk volume of water, lithology, gas effect, P-wave velocity, movable hydrocarbon index and irreducible water saturation and integrated with different cross-plots. The Eocene reservoirs are excellent with high effective porosity (2–32 %) and hydrocarbon saturation (10–93 %). Among these, the Sui Upper Limestone is an overall a poor reservoir; however, it has some hydrocarbon-rich intervals with high effective porosity and better net pay. All the net pay zones identified show low and variable shale volume (5–30 %). The secondary porosity has added to the total and effective porosities in these reservoirs. The main contributors to the porosity are the chalky, intercrystalline and vuggy/fracture types. The thickness of the reservoirs zones ranges from 4.5 to 62 m. These reservoirs are gas-producing carbonates with almost irreducible water saturation (0.002–0.01) and are likely to produce water-free hydrocarbons. The lower values of moveable hydrocarbon index (0.07–0.9) show that the hydrocarbons are moveable spontaneously to the well bore. The proposed correlation model shows that the reservoirs have an inclined geometry and are a part of an anticlinal trap.     

Determination of sand dune characteristics through geomorphometry and wind data analysis in central Iran (Kashan Erg)

The combination of wind measurements and remotely sensed geomorphometry indices provides a valuable resource in the study of desert landforms, because arduous desert environments are difficult to access. In this research, we couple wind data and geomorphometry to separate and classify different sand dunes in Kashan Erg in central Iran. Additionally, the effect of sand-fixing projects on sand dune morphology was assessed using geomorphometry indices (roughness, curvature, surface area, dune spacing and dune height). Results showed that a Digital Elevation Model of the National Cartographic Center of Iran (NCC DEM) with 10-m resolution and accuracy of 54% could discriminate geomorphometry parameters better than the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data with 30-m resolution and Shuttle Radar Topography Mission (SRTM) data with 90-m resolution and 45.2 and 1.6% accuracy, respectively. Low classification of SRTM DEM was associated with too many non-value points found in the DEM. Accuracy assessment of comparison ground control points revealed that ASTER DEM (RMSE = 4.25) has higher accuracy than SRTM and NCC DEMs in this region. Study of curvature showed that transverse and linear sand dunes were formed in concave topography rather than convex. Reduced slopes in fixed sand dunes were established due to wind erosion control projects. Measurements of dune height and spacing show that there is significant correlation in compound dunes (R ² = 0.546), linear dunes (R ² = 0.228) and fixed dunes (R ² = 0.129). In general, the height of dunes in Kashan Erg increases from the margin of the field to the center of the field with a maximum height of 120 m in star dunes. Analysis of wind data showed that sand drift potential is in low-medium class in Kashan Erg. Linear sand dunes in Kashan Erg show that they are following a global trend in forming of these. Finally, established of geomorphometry method in dune classification will help researchers to identify priority of land management and performance assessment of sand dunes fixing projects in arid arduous environment.     

Prediction of rainfall using artificial neural networks for synoptic station of Mashhad: a case study

In this paper, we have utilized ANN (artificial neural network) modeling for the prediction of monthly rainfall in Mashhad synoptic station which is located in Iran. To achieve this black-box model, we have used monthly rainfall data from 1953 to 2003 for this synoptic station. First, the Hurst rescaled range statistical (R/S) analysis is used to evaluate the predictability of the collected data. Then, to extract the rainfall dynamic of this station using ANN modeling, a three-layer feed-forward perceptron network with back propagation algorithm is utilized. Using this ANN structure as a black-box model, we have realized the complex dynamics of rainfall through the past information of the system. The approach employs the gradient decent algorithm to train the network. Trying different parameters, two structures, M₅₃₁ and M₇₄₁, have been selected which give the best estimation performance. The performance statistical analysis of the obtained models shows with the best tuning of the developed monthly prediction model the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) are 0.93, 0.99, and 6.02 mm, respectively, which confirms the effectiveness of the developed models.     

Evaluating the support vector machine for suspended sediment load forecasting based on gamma test

Due to the various influencing factors on river suspended sediment transportation, determining an appropriate input combination for developing the suspended sediment load forecasting model is very important for water resources management. The influence of pre-processing of input variables by Gamma Test (GT) was investigated on performance of Support Vector Machine (SVM) with two kernels; Radial Basis Function (RBF) and polynomial in order to forecast daily suspended sediment amount in the period between 1983 and 2014 at Korkorsar basin, northern Iran. The best input combination was identified using GT and correlation coefficient analysis. Then, the SVM model was developed and the suspended sediment amount was forecasted with RBF and polynomial kernels. The obtained results in testing phase showed that GT-SVM (RBF kernel) model can estimate suspended sediment more accurately with the lowest RMSE (14.045 ton/day), highest correlation coefficient (0.88) and highest NSEC coefficient (0.88) than SVM (RBF kernel) model (RMSE?=?18.36ton/day, \( {R}^2=0.79, \) \( NSEC=0.73 \)) and had a better performance than the other models. The results indicated that in forecasting the first nine maximum values of suspended sediment load, GT-SVM (RBF) had a higher capability than the other models and could provide a more accurate estimation from the maximum rate of suspended sediment. The results of this study showed the capability of identifying the priority of the input parameters can change GT to a useful and technical test for input variables pre-processing to forecast the amount of suspended sediments.     

Role of early warning systems for sustainable agriculture in Iran

Drought is a complex phenomenon in meteorology and can affect agriculture. Its impacts vary greatly since they depend not only on the magnitude, timing, duration, and frequency of rainfall deficits but also on the differing responses of various plants to water stress. The essence of good drought management is to use this range of responses to the best advantage. Iran is one of the world’s largest and most productive suppliers of food and fiber. The objective of this study was, therefore, to gather and analyze standardized information on the Role of Early Warning Systems for Sustainable Agriculture for cereals and leguminous and industrial crops in Iran environmental zones. Annual average rainfall (mm year^?1) and ET_O (mm year^?1) are 76.56 and 3001, respectively, in stations with very dry climate; 195.41 and 2249, respectively, in stations with dry climate; 343.9 and 1351, respectively, in stations with semi-dry climate; 583.8 and 1153, respectively, in stations with semi-humid climate; and 1272 and 949, respectively, in stations with humid climate. The maximum and minimum of annual average rainfall happened in Rasht (1337 mm year^?1) and Zabol (57 mm year^?1) stations, and the maximum and minimum for annual average ET_O happened in Chabahar (3909.15 mm year^?1) and Anzali harbor (890.6 mm year^?1), respectively. Therefore, 13.63 % of stations have suitable conditions for crop productions and 86.37 % are in critical conditions.