Topic Modelling and Sentiment Analysis of Global Warming Tweets

With the increasing extreme weather events and various disasters, people are paying more attention to environmental issues than ever, particularly global warming. Public debate on it has grown on various platforms, including newspapers and social media. This paper examines the topics and sentiments of the discussion of global warming on Twitter over a span of 18 months using two big data analytics techniques—topic modelling and sentiment analysis. There are seven main topics concerning global warming frequently debated on Twitter: factors causing global warming, consequences of global warming, actions necessary to stop global warming, relations between global warming and Covid-19; global warming’s relation with politics, global warming as a hoax, and global warming as a reality. The sentiment analysis shows that most people express positive emotions about global warming, though the most evoked emotion found across the data is fear, followed by trust. The study provides a general and critical view of the public’s principal concerns and their feelings about global warming on Twitter.

Big Data Analytics for Long-Term Meteorological Observations at Hanford Site

A growing number of physical objects with embedded sensors with typically high volume and frequently updated data sets has accentuated the need to develop methodologies to extract useful information from big data for supporting decision making. This study applies a suite of data analytics and core principles of data science to characterize near real-time meteorological data with a focus on extreme weather events. To highlight the applicability of this work and make it more accessible from a risk management perspective, a foundation for a software platform with an intuitive Graphical User Interface (GUI) was developed to access and analyze data from a decommissioned nuclear production complex operated by the U.S. Department of Energy (DOE, Richland, USA). Exploratory data analysis (EDA), involving classical non-parametric statistics, and machine learning (ML) techniques, were used to develop statistical summaries and learn characteristic features of key weather patterns and signatures. The new approach and GUI provide key insights into using big data and ML to assist site operation related to safety management strategies for extreme weather events. Specifically, this work offers a practical guide to analyzing long-term meteorological data and highlights the integration of ML and classical statistics to applied risk and decision science.

Perception of Climate Change Effects over Time and the Contribution of Different Areas of Knowledge to Its Understanding and Mitigation

Climate change is a current subject that is attracting more and more attention, whether from academics or the public. This public attention is mainly due to the frequently published news in the media, reporting consequences caused by extreme weather events. On the other hand, scientists are looking into the origins of the phenomenon, seeking answers that will somehow help to mitigate the effects of climate change. This article presents a review of some of the different possible approaches taken on climate change, to demonstrate the need to build a multidisciplinary perspective of the problem. It is understood that only the integration of different perspectives, presented by different areas of knowledge, such as natural sciences, social and economic sciences and human sciences, will make it possible to build modeling and predictive scenarios, which realistically may represent the development of the earth system under the influence of climate change. In this way, with the support of all areas of knowledge, the creation of forecast models where all possible changes to the different variables of the earth system may be simulated will allow for the mitigation measures presented to be analyzed in advance and, thus, prioritized. This review shows that a multi and interdisciplinary approach, based on the knowledge acquired from different knowledge and science fields, presents itself as the way to solve this global and complex problem caused by climate change.

Endless November? Citizen Beliefs Concerning Wood As A Construction Material Under Extreme Weather Events

Climate change places great pressure on the construction sector to decrease its greenhouse gas emissions and to create solutions that perform well in changing weather conditions. In the urbanizing world, wood construction has been identified as one of the opportunities for mitigating these emissions. Our study explores citizen opinions on wood usage as a building material under expected mitigation and adaptation measures aimed at a changing climate and extreme weather events. The data are founded on an internet-based survey material collected from a consumer panel from Finland and Sweden during May–June 2021, with a total of 2015 responses. By employing exploratory factor analysis, we identified similar belief structures for the two countries, consisting of both positive and negative views on wood construction. In linear regressions for predicting these opinions, the perceived seriousness of climate change was found to increase positive views on wood construction but was insignificant for negative views. Both in Finland and Sweden, higher familiarity with wooden multistory construction was found to connect with more positive opinions on the potential of wood in building, e.g., due to carbon storage properties and material attributes. Our findings underline the potential of wood material use as one avenue of climate change adaptation in the built environment. Future research should study how citizens’ concerns for extreme weather events affect their future material preferences in their everyday living environments, also beyond the Nordic region.

A Modeling and Analysis Framework for Integrated Energy Systems Exposed to Climate Change-Induced NaTech Accidental Scenarios

This paper proposes a novel framework for the analysis of integrated energy systems (IESs) exposed to both stochastic failures and “shock” climate-induced failures, such as those characterizing NaTech accidental scenarios. With such a framework, standard centralized systems (CS), IES with distributed generation (IES-DG) and IES with bidirectional energy conversion (IES+P2G) enabled by power-to-gas (P2G) facilities can be analyzed. The framework embeds the model of each single production plant in an integrated power-flow model and then couples it with a stochastic failures model and a climate-induced failure model, which simulates the occurrence of extreme weather events (e.g., flooding) driven by climate change. To illustrate how to operationalize the analysis in practice, a case study of a realistic IES has been considered that comprises two combined cycle gas turbine plants (CCGT), a nuclear power plant (NPP), two wind farms (WF), a solar photovoltaicS (PV) field and a power-to-gas station (P2G). Results suggest that the IESs are resilient to climate-induced failures.

Analyze the Outbreak of COVID-19 in Wuhan City Based on Large-Scale Events and Extreme Weather

This article analyzes the impact of large-scale mass activities and extreme weather on the outbreak of COVID-19 in Wuhan, confirming that the South China Seafood Market is indeed the origin of the Wuhan epidemic, and found that the probability of respiratory transmission is low in open space, while food transmission is possible. At the same time, it was found that the outbreaks of SARS in Beijing in 2003 and COVID-19 in Wuhan in 2019 were both related to extreme weather. By investigating genomics and epidemiological data, it was determined that the first COVID-19 case in Wuhan was in November, and the beginning of the epidemic was in late November. Comparing the climate of November, December and January in Wuhan from 2011 to 2020, it is found that there are a lot of extreme weather events in Wuhan from the end of 2019 to the beginning of 2020, including strong winds, heavy rains, large cooling after continuous high temperature, and continuous low temperature and rainy after large cooling, the temperature suddenly rises and then drops rapidly, the wind continues to weaken for many days and then suddenly increases, and long rainy days, etc.

Farm Parcel Extraction in High Resolution Remote Sensing Image Based on Hierarchical Spectrum and Shape Features

Background: Land-use classification schemes typically address both land use and land cover. Vectorized data extracted from farm parcel segmentation provides important cadastral data for the formulation and management of climate change policies. It also provides important basic data for research on pest control in large areas, crop yield forecasts, and crop varieties classification. It can also be used for the assessment of compensation for damages related to extreme weather events by the agricultural insurance department. Firstly, we investigate the effectiveness of an automated image segmentation method based on TransUNet architecture to enable that automate the task of farm parcel delineation that originally relied on high labor costs. Then, post-processing by vectoring binary segmentation image, which the area and regularity parameter to adjust the accuracy of segmentation, can get a more optimized image segmentation result.Results: The results on the existing data show that the automatic segmentation system we proposed is a method that can effectively divide various types of agricultural land. The system was trained and evaluated using 94780 images. The performance parameters obtained showed that the accuracy rate reached 83.31%, the recall rate reached 82.13%, the F1-S rate was 80.37%, the total accuracy rate was 82.23%, and Iou was 80.39%. At the same times, without losing too much accuracy, we train and test the model with 3m resolution image, which has the advantage of processing speed than 0.8m resolution. Therefore, our proposed method can be effectively applied to the task of extraction of agricultural land, which is better and more efficient than most manual annotations.Conclusions: We have demonstrated the effectiveness of strategy using a TransUNet architecture and postprocessing by vectoring binary segmentation for farm parcel extraction in high remote sensing images. The success of our approach is also a demonstration of feasibility of the deep learning to participate in and improve agricultural production activities, which is important for achieving scientific management of agricultural production.