The JET 2019-2020 scientific and technological programme exploited the results of years of concerted scientific and engineering work, including the ITER-like wall (ILW: Be wall and W divertor) installed in 2010, improved diagnostic capabilities now fully available, a major Neutral Beam Injection (NBI) upgrade providing record power in 2019-2020, and tested the technical & procedural preparation for safe operation with tritium. Research along three complementary axes yielded a wealth of new results. Firstly, the JET plasma programme delivered scenarios suitable for high fusion power and alpha particle physics in the coming D-T campaign (DTE2), with record sustained neutron rates, as well as plasmas for clarifying the impact of isotope mass on plasma core, edge and plasma-wall interactions, and for ITER pre-fusion power operation. The efficacy of the newly installed Shattered Pellet Injector for mitigating disruption forces and runaway electrons was demonstrated. Secondly, research on the consequences of long-term exposure to JET-ILW plasma was completed, with emphasis on wall damage and fuel retention, and with analyses of wall materials and dust particles that will help validate assumptions and codes for design & operation of ITER and DEMO. Thirdly, the nuclear technology programme aiming to deliver maximum technological return from operations in D, T and D-T benefited from the highest D-D neutron yield in years, securing results for validating radiation transport and activation codes, and nuclear data for ITER.

Alpha particles with energies on the order of megaelectronvolts will be the main source of plasma heating in future magnetic confinement fusion reactors. Instead of heating fuel ions, most of the energy of alpha particles is transferred to electrons in the plasma. Furthermore, alpha particles can also excite Alfvénic instabilities, which were previously considered to be detrimental to the performance of the fusion device. Here we report improved thermal ion confinement in the presence of megaelectronvolts ions and strong fast ion-driven Alfvénic instabilities in recent experiments on the Joint European Torus. Detailed transport analysis of these experiments reveals turbulence suppression through a complex multi-scale mechanism that generates large-scale zonal flows. This holds promise for more economical operation of fusion reactors with dominant alpha particle heating and ultimately cheaper fusion electricity.

The forecasting of air pollution is an important and popular topic in environmental engineering. Due to health impacts caused by unacceptable particulate matter (PM) levels, it has become one of the great est concerns in metropolitan cities like Karaj City in Iran. In this study, the concentration of PM 2.5 was predicted by applying a multilayer percepteron (MLP) neural network, a radial basis function (RBF) neural network and a Markov chain model. Two months of hourly data including temperature, NO, NO 2 , NO x , CO, SO 2 and PM 10 were used as inputs to the artifi cial neural networks. From 1,488 data, 1,300 of data was used to train the models and the rest of the data were applied to test the models. The results of using artificial neural networks indicated that the models performed well in predicting PM 2.5 concen trations. The application of a Markov chain described the probable occurrences of unhealthy hours. The MLP neural network with two hidden layers including 19 neurons in the first layer and 16 neurons in the second layer provided the best results. The coeffi cient of determination (R 2 ), Index of Agreement (IA) and Efficiency (E) between the observed and the predicted data using an MLP neural network were 0.92, 0.93 and 0.981, respectively. In the MLP neu ral network, the MBE was 0.0546 which indicates the adequacy of the model. In the RBF neural net work, increasing the number of neurons to 1,488 caused the RMSE to decline from 7.88 to 0.00 and caused R 2 to reach 0.93. In the Markov chain model the absolute error was 0.014 which indicated an ac ceptable accuracy and precision. We concluded the probability of occurrence state duration and transi tion of PM 2.5 pollution is predictable using a Markov chain method.

The complicated non‐linear relationships between water quality and environmental parameters involved in predicting algal blooms necessitate a new approach, using data‐driven modelling. Accordingly, a multilayer perceptron (MLP) and time delay neural network (TDNN) were used to predict the eutrophication status of two monitoring stations in the Amirkabir Reservoir in Iran. Six scenarios for each monitoring station were performed to select a significant, independent input using 12 years of monthly data. The final inputs were temperature, turbidity, phosphate (PO4), nitrate (NO3), nitrite (NO2), ammonium (NH3), dissolved oxygen (DO) and electrical conductivity (EC). Applying an MLP neural network to the upstream monitoring station with 21–38 neurons in the first and second hidden layers, the minimum mean squared errors (MSE) in training, validating and testing were 0.083, 0.81 and 1.95 cells/100 ml, respectively. Further, when the TDNN network was used with the same neuron numbers in the hidden layer for the similar monitoring station, the minimum MSE values for model training, validating and testing were 0.06, 0.72 and 1.76 cells/100 ml, respectively. For the Beylaghan monitoring station, using the MLP neural network with 29–23 neurons in the first and second hidden layer, the minimum MSE values gained in training, validating and testing were 0.181, 0.58 and 0.95 cells/100 ml, respectively. Using the TDNN network with the same neurons in the hidden layers of the MLP neural network for the station, the minimum MSE values for training, validating and testing were 0.152, 0.43 and 0.84 cells/100mL, respectively. Thus, TDNN exhibited a high accuracy and workability, compared to the MLP. Sensitivity analysis of the Amirkabir Reservoir dataset indicated increasing the value of nitrate is the first factor, followed by turbidity and NH3, having the greatest impacts on eutrophication prediction.