FLOOD STAGE FORECASTING WITH SUPPORT VECTOR MACHINES1

ABSTRACT: Machine learning techniques are finding more and more applications in the field of forecasting. A novel regression technique, called Support Vector Machine (SVM), based on the statistical learning theory is explored in this study. SVM is based on the principle of Structural Risk Minimization as opposed to the principle of Empirical Risk Minimization espoused by conventional regression techniques. The flood data at Dhaka, Bangladesh, are used in this study to demonstrate the forecasting capabilities of SVM. The result is compared with that of Artificial Neural Network (ANN) based model for one‐lead day to seven‐lead day forecasting. The improvements in maximum predicted water level errors by SVM over ANN for four‐lead day to seven‐lead day are 9.6 cm, 22.6 cm, 4.9 cm and 15.7 cm, respectively. The result shows that the prediction accuracy of SVM is at least as good as and in some cases (particularly at higher lead days) actually better than that of ANN, yet it offers advantages over many of the limitations of ANN, for example in arriving at ANN's optimal network architecture and choosing useful training set. Thus, SVM appears to be a very promising prediction tool.     

A LARGE ELECTRONIC WEIGHING LYSIMETER SYSTEM: DESIGN AND INSTALLATION1

ABSTRACT: To measure crop evapotranspiration, a large double tank, electronic weighting lysimeter system was designed and installed at the Shahid Bahonar University farm, Kerman, Iran. The system was installed in a 50 m² underground building. It includes two tanks of 3.00 m in diameter and 1.75 m deep. The weighing mechanism for each tank is a set of three compression strain gage load cells, which are fixed on 1.20 m height column above the floor. According to the specification of the load cells, the maximum possible weighing error may be about 0.01 percent of total mass, which is equivalent to 0.28 mm of water, but the measured error was equal to 1 kg mass, which is equivalent to 0.14 mm of water. The load cell data from each tank and the on‐site environmental data (temperature, humidity, and wind velocity and direction) are automatically recorded and saved in a personal computer hard disk for further use and analysis.     

A MATHEMATICAL MODEL OF SALMONID SPAWNING HABITAT1

ABSTRACT: A simulation model [Salmonid Spawning Analysis Model (SSAM)] was developed as a management tool to evaluate the relative impacts of stream sediment load and water temperature on salmonid egg survival. The model is useful for estimating acceptable sediment loads to spawning habitat that may result from upland development, such as logging and agriculture. Software in common use in the USA were adapted for use in gravel bedded rivers and linked to simulate water temperature (the USFWS Instream Water Temperature, SNTEMP model) and water and sediment routing (the USAE Scour and Deposition in Rivers and Reservoirs, HEC-6 model, version 3.2). These models drive the redd (spawning nest) model (the USDA-ABS Sediment Intrusion Dissolved Oxygen SIDO model) which simulates sediment intrusion and dissolved oxygen concentration in the redd environment. The SSAM model predictions of dissolved oxygen and water temperature compared favorably with field data from artificial redds containing hatchery chinook salmon eggs.     

FACTORS THAT AFFECT ACTIVATED SLUDGE PHOSPHATE RELEASE1

The activated sludge process can remove significant amounts of phosphorus from sewage, but the removal efficiency is usually significantly reduced by the release of phosphate back to solution during subsequent treatment steps. This research presents a study of soluble phosphate release from activated sludge with emphasis on defining the factors that affect such release and the actual release mechanisms. Laboratory units were used for experimental purposes. The experiments were designed to study the relationship between soluble phosphate release and various environmental factors such as redox potential (ORP), dissolved oxygen (DO), pH, solids concentration, solids destruction, and sulfate salt addition. The effect of substrate utilization on phosphate uptake and the relationship between uptake characteristics and subsequent phosphate release were also studied. The results show that some phosphate storage occurs during aerobic substrate utilization. Following substrate utilization, activated sludge phosphate release is directly related to the amount of biological stress the organisms are subjected to, and the mechanism of release is primarily cell lysis. The phosphate released per unit sludge under anoxic conditions is relatively constant. Under normal environmental conditions, neither ORP or pH change have a significant affect on phosphate release.     

Applying tqm to environmental site assessments under the astm standard

Total Quality Management was initially developed to facilitate an ethos of continuous improvement of the production process. It entails both an internal and external focus. The former depends on a cooperative effort among employees at all levels of the organization to analyze work processes, minimize process variance, and thereby maximize productivity. The latter requires close collaboration with suppliers to ensure that raw or processed materials can be readily and efficiently integrated into the production process and constant communication with the end user—the customer—to ensure that the process generates the expected level of quality. Applying TQM to service industry processes is a bit more complex. In addition to having to tailor the TQM approach to the specific service industry, the processes are seldom identical and tend not to lend themselves to the same type of statistical variance analysis that is considered a hallmark of TQM. Nevertheless, numerous case studies have shown that TQM is applicable to the service industry and can help to generate a culture of continuous improvement and enhance customer satisfaction. Environmental site assessments provide a unique challenge to proponents of TQM. Construction, geological, and hydrological characteristics are unique at each site; regulatory requirements differ by jurisdiction; access to historical information is inconsistent; auditors have varying backgrounds; and client needs and expectations differ. Nevertheless, as the American Society for Testing and Materials (ASTM) standard practice gains acceptance as a benchmark for environmental site assessments, the application of TQM practices to this service process becomes more practicable.     

Correlations in the chemical composition of rural background atmospheric aerosol in the UK determined in real time using time-of-flight mass spectrometry

An aerosol time-of-flight mass spectrometer (ATOFMS) was used to determine, in real time, the size and chemical composition of individual particles in the atmosphere at the remote inland site of Eskdalemuir, Scotland. A total of 51,980 particles, in the size range 0.3-7.4 microm, were detected between the 25th and 30th June 2001. Rapid changes in the number density, size and chemical composition of the atmospheric aerosol were observed. These changes are attributed to two distinct types of air mass; a polluted air mass that had passed over the British mainland before reaching Eskdalemuir, interposed between two cleaner air masses that had arrived directly from the sea. Such changes in the background aerosol could clearly be very important to studies of urban aerosols and attempts at source apportionment. The results of an objective method of data analysis are presented. Correlations were sought between the occurrence of: lithium, potassium, rubidium, caesium, beryllium, strontium, barium, ammonium, amines, nitrate, nitrite, boron, mercury, sulfate, phosphate, fluorine, chlorine, bromine, iodine and carbon (both elemental and organic hydrocarbon) in both fine (d < 2.5 microm) and coarse (d > 2.5 microm) particle fractions. Several previously unreported correlations were observed, for instance between the elements lithium, beryllium and boron. The results suggest that about 2 in 3 of all fine particles (by number rather than by mass), and 1 in 2 of all coarse particles containing carbon, consisted of elemental carbon rather than organic hydrocarbon (although a bias in the sensitivity of the ATOFMS could have affected these numbers). The ratio of the number of coarse particles containing nitrate anions to the number of particles containing chloride anions exceeded unity when the air mass had travelled over the British mainland. The analysis also illustrates that an air mass of marine origin that had travelled slowly over agricultural land can accumulate amines and ammonium.     

The ecological relevance of current approaches for environmental protection from exposure to ionising radiation

This paper discusses the current approaches to environmental protection from ionising radiation from an ecological perspective, highlighting the need to understand fully what we are trying to protect. Ecologically relevant endpoints for environmental protection are discussed along with the need to integrate protection from ionising radiation with the approaches adopted for non-radioactive contaminants. A possible integrated assessment approach is outlined.