Performances of Different Machine Learning Algorithms for Predicting Saltwater Intrusion in the Vietnamese Mekong Delta Using Limited Input Data: A Study from Ham Luong River

Water Resources - Accurate forecasting of salinity intrusion has a vital role in water resource management to mitigate and prevent its adverse effects. However, monitoring of salinity presents...     

Effect of fines content on soil freezing characteristic curve of sandy soils

Acta Geotechnica - Soil freezing characteristic curve (SFCC) represents the relationship between soil temperature and unfrozen water content of soil during freezing and thawing processes. In this...     

Continental Scale Hydrostratigraphy: Comparing Geologically Informed Data Products to Analytical Solutions

This study synthesizes two different methods for estimating hydraulic conductivity (K) at large scales. We derive analytical approaches that estimate K and apply them to the contiguous United States. We then compare these analytical approaches to three-dimensional, national gridded K data products and three transmissivity (T) data products developed from publicly available sources. We evaluate these data products using multiple approaches: comparing their statistics qualitatively and quantitatively and with hydrologic model simulations. Some of these datasets were used as inputs for an integrated hydrologic model of the Upper Colorado River Basin and the comparison of the results with observations was used to further evaluate the K data products. Simulated average daily streamflow was compared to daily flow data from 10 USGS stream gages in the domain, and annually averaged simulated groundwater depths are compared to observations from nearly 2000 monitoring wells. We find streamflow predictions from analytically informed simulations to be similar in relative bias and Spearman's rho to the geologically informed simulations. R-squared values for groundwater depth predictions are close between the best performing analytically and geologically informed simulations at 0.68 and 0.70 respectively, with RMSE values under 10 m. We also show that the analytical approach derived by this study produces estimates of K that are similar in spatial distribution, standard deviation, mean value, and modeling performance to geologically-informed estimates. The results of this work are used to inform a follow-on study that tests additional data-driven approaches in multiple basins within the contiguous United States.     

Remote sensing and avian influenza: A review of image processing methods for extracting key variables affecting avian influenza virus survival in water from Earth Observation satellites

Recent studies have highlighted the potential role of water in the transmission of avian influenza (AI) viruses and the existence of often interacting variables that determine the survival rate of these viruses in water; the two main variables are temperature and salinity.     

Multi-instrument remote and in situ observations of the Erebus Volcano (Antarctica) lava lake in 2005: A comparison with the Pele lava lake on the jovian moon Io

The stable, persistent, active lava lake at Erebus volcano (Ross Island, Antarctica) provides an excellent thermal target for analysis of spacecraft observations, and for testing new technology. In the austral summer of 2005 visible and infrared observations of the Erebus lava lake were obtained with sensors on three space vehicles Terra (ASTER, MODIS), Aqua (MODIS) and EO-1 (Hyperion, ALI). Contemporaneous ground-based observations were obtained with hand-held infrared cameras. This allowed a quantitative comparison of the thermal data obtained from different instruments, and of the analytical techniques used to analyze the data, both with and without the constraints imposed by ground-truth. From the thermal camera data, in December 2005 the main Erebus lava lake (Ray Lake) had an area of ≈ 820 m². Surface colour temperatures ranged from 575 K to 1090 K, with a broad peak in the distribution from 730 K to 850 K. Total heat loss was estimated at 23.5 MW. The flux density was ≈ 29 kW m^− 2. Mass flux was estimated at 64 to 93 kg s^− 1. The best correlation between thermal emission and emitting area was obtained with ASTER, which has the best combination of spatial resolution and wavelength coverage, especially in the thermal infrared. The high surface temperature of the lava lake means that Hyperion data are for the most part saturated. Uncertainties, introduced by the need to remove incident sunlight cause the thermal emission from the Hyperion data to be a factor of about two greater than that measured by hand-held thermal camera. MODIS also over-estimated thermal output from the lava lake by the same factor of two because it was detecting reflected sunlight from the rest of the pixel area. The measurement of the detailed temperature distribution on the surface of an active terrestrial lava lake will allow testing of thermal emission models used to interpret remote-sensing data of volcanism on Io, where no such ground-truth exists. Although the Erebus lava lake is four orders of magnitude smaller than the lava lake at Pele on Io, the shape of the integrated thermal emission spectra are similar. Thermal emission from this style of effusive volcanism appears to be invariant. Excess thermal emission in most Pele spectra (compared to Erebus) at short wavelengths (< 3 μm) is most likely due to disruption of the surface on the lava lake by escaping volatiles.     

A comparative study of three different learning algorithms applied to ANFIS for predicting daily suspended sediment concentration

The modeling and prediction of suspended sediment in a river are key elements in global water recourses and environment policy and management. In the present study, an Adaptive Neuro-Fuzzy Inference System model trained with the Levenberg-Marquardt learning algorithm is considered for time series modeling of suspended sediment concentration in a river. The model is trained and validated using daily river discharge and suspended sediment concentration data from the Schuylkill River in the United States. The results of the proposed method are evaluated and compared with similar networks trained with the common Hybrid and Back-Propagation algorithms, which are widely used in the literature for prediction of suspended sediment concentration. Obtained results demonstrate that models trained with the Hybrid and Levenberg-Marquardt algorithms are comparable in terms of prediction accuracy. However, the networks trained with the Levenberg-Marquardt algorithm perform better than those trained with the Hybrid approach.     

Geochemical and geochronological studies of the Muong Hum alkaline granitic pluton from the Phan Si Pan Zone,northwest Vietnam: Implications for petrogenesis and tectonic setting

The Phan Si Pan zone in northwest Vietnam is an important tectonic unit for understanding the geological evolution of the southeast Asian Block. Numerous late Permian A‐type granites outcrop in this zone. In this study, new geochemical and geochronological data derived from the Muong Hum alkaline granitic pluton in the Phan Si Pan zone were investigated for its petrogenesis and tectonic setting. Zircon U–Pb analyses of three samples yielded ²⁰⁶Pb/²³⁸U ages of (251.1 ±3.5) Ma, (251.2 ±3.8) Ma, and (253.9 ±1.5) Ma, respectively, coinciding with the ages of the acid member of magma from Emeishan large igneous province, southwest China. The Muong Hum granite has 10 000 × Ga/Al and A/CNK values of 4.70–4.93 and 0.87–0.90, respectively, as well as negative Eu anomalies. It shows significant depletion of Ba, Sr, Ti, and P, similar to features of A‐type granite. Zircons have positive ε_Hf(t) values (+1.9 to +8.6) and Hf model ages (T_DM1) of 595–846 Ma, originating a mantle source. Compared with the Panzhihua A‐type granite of the southwest China domain and other A‐type plutons of the Phan Si Pan zone, including Ye Yen Sun, Phu Sa Phin, Nam Xe, Tam Duong Phan Si Pan, and Taihe, the geochemical characteristics and zircon Hf isotopic compositions of the Muong Hum granite demonstrate an affinity of mantle magma. It is believed that the Phan Si Pan zone is an important part of Emeishan large igneous province. It was reworked by the Cenozoic Aillaoshan‐Red River shear fault to its present location.