Climate change is undoubtedly one of the biggest problems in the 21st century. Currently, however, most research efforts on climate forecasting are based on mechanistic, bottom-up approaches such as physics-based general circulation models and earth system models. In this study, we explore the performance of a phenomenological, top-down model constructed using a neural network and big data of global mean monthly temperature. By generating graphical images using the monthly temperature data of 30 years, the neural network system successfully predicts the rise and fall of temperatures for the next 10 years. Using LeNet for the convolutional neural network, the accuracy of the best global model is found to be 97.0%; we found that if more training images are used, a higher accuracy can be attained. We also found that the color scheme of the graphical images affects the performance of the model. Moreover, the prediction accuracy differs among climatic zones and temporal ranges. This study illustrated that the performance of the top-down approach is notably high in comparison to the conventional bottom-up approach for decadal-scale forecasting. We suggest using artificial intelligence-based forecasting methods along with conventional physics-based models because these two approaches can work together in a complementary manner.

Analyzing and utilizing spatiotemporal big data are essential for studies concerning climate change. However, such data are not fully integrated into climate models owing to limitations in statistical frameworks. Herein, we employ VARENN (visually augmented representation of environment for neural networks) to efficiently summarize monthly observations of climate data for 1901–2016 into two-dimensional graphical images. Using red, green, and blue channels of color images, three different variables are simultaneously represented in a single image. For global datasets, models were trained via convolutional neural networks. These models successfully classified the rises and falls in temperature and precipitation. Moreover, similarities between the input and target variables were observed to have a significant effect on model accuracy. The input variables had both seasonal and interannual variations, whose importance was quantified for model efficacy. We successfully illustrated the importance of short-term (monthly) fluctuations in the model accuracy, suggesting that our AI-based approach grasped some previously unknown patterns that are indicators of succeeding climate trends. VARENN is thus an effective method to summarize spatiotemporal data objectively and accurately.

No abstract

No abstract

Autoradiography using imaging plates is a conventional method for the visualization of the distribution of radionuclides. Imaging plates have high sensitivity to the charged particles of α- and β-rays but are also sensitive to γ-rays. When the radioactivity level in the sample is low, a longer exposure time is needed, and shielding of the natural background radiation is necessary. Large imaging plates (e.g., 35 × 40 cm), which can obtain the radioactivity distribution over a wider area, were developed. In this work, a low-background shielding box is developed for large imaging plates, and the shielding characteristics of the box and sensitivities of the imaging plate to α-, β-, and γ-rays are quantitatively investigated. It is shown, by considering the sensitivity of imaging plates to α-, β-, and γ-rays, that most images of environmental samples are the result of α- or β-rays emitted from radionuclides at the sample surface, but not from the whole sample. To exemplify autoradiography using the presented shielding box, some environmental samples contaminated with radioactive fallout from the Fukushima Daiichi Nuclear Power Plant accident are measured. The distribution of radionuclides is clearly visualized and, furthermore, information of the migration of radiocesium in the sample is obtained.