Machine learning for predictive management: short and long term prediction of phytoplankton biomass using genetic algorithm based recurrent neural networks

In the regulated Nakdong River, algal proliferations are annually observed in some seasons, with cyanobacteria [Microcystis aeruginosa] appearing in summer and diatom blooms [Stephanodiscus hantzschii] in winter. This study aims to develop two ecological models forecasting future chlorophyll a at two time-steps [one-week and one-year forecasts], using recurrent neural networks tuned by genetic algorithm [GA-RNN]. A moving average [MA] method pre-processes the data for both short- and long-term forecasting to evaluate the effect of noise downscaling on model predictability and to estimate its usefulness and trend prediction for management purposes. Twenty-five physicochemical and biological components [e.g. water temperature, DO, pH, dams discharge, river flow, rainfall, zooplankton abundance, nutrient concentration, etc. from 1994 to 2006] are used as input variables to predict chlorophyll a GA-RNN models show a satisfactory level of performance for both predictions. Using genetic operations in the network training enables us to avoid numerous trial-and-error model constructions. MA-smoothed data improves the predictivity of models by removing residuals in the data prediction and enhancing the trend of time-series patterns. The results demonstrate efficient development of ecological models through selecting appropriate network structures. Data pre-processing with MA helps in forecasting long-term seasonality and trend of chlorophyll alpha, an important outcome for decision makers because it provides more reaction time to establish and control management strategies

Dose estimation with the calibration of dose-response curve of micronucleus in human peripheral lymphocytes induced by 50MeV proton beams

The purpose of this paper is to establish an easy and reliable biodosimeter protocol to evaluate the biological effects of proton beams. Human peripheral blood lymphocytes were irradiated using proton beams [LET: 34.6 keV micro m[-1]], and the chromosome aberrations induced were analyzed using cytokinesis-blocked [CB] micronucleus [MN] assay. To determine the efficiency of MN assay in estimating the doses received by 50MeV proton beams and to monitor predicted dose of victims in accidental exposure, here we have evaluated the performance of MN analysis in a simulated situation after exposure with proton beams. Peripheral lymphocytes were irradiated by 50MeV proton beams up to 6Gy and analyzed by Giemsa staining of CB MN assay. The detected MN was found to be a significant dose-effect curve in the manner of dose-dependent increase after exposure with proton beams in vitro. When plotting on a linear scale against radiation dose, the line of best fit was Y=0.004+[1.882x10[-2] +/- 9.701x10[-5]] D+[1.43x10[-3] +/- 1.571x10[-5]]D2. Our results show a trend towards increase of the number of MN with increasing dose. It was linear-quadratic and has a significant relationship between the frequencies of MN and dose [R2= 0.9996]. The number of MN in lymphocyte that was observed in control group is 5.202 +/- 0.04/cell. Hence, this simple protocol will be particularly useful for helping physicians to decide medical therapy for the initial treatment of victims with rapid and precise dose estimation after accidental radiation exposure. Also it has potential for use as a valuable biomarker to evaluate the biological effectiveness for cancer therapy with proton beams