Deep Learning for Detecting Extreme Weather Patterns

2021 ◽  
pp. 161-185
Author(s):  
Mayur Mudigonda, Prabhat Ram ◽  
Karthik Kashinath ◽  
Evan Racah ◽  
Ankur Mahesh ◽  
Yunjie Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Extreme Weather ◽  
Weather Patterns

scholarly journals Combining AI and Analog Forecasting to Predict Extreme Weather

Eos ◽  
2020 ◽  
Vol 101 ◽  
Author(s):  
Richard Sima
Keyword(s):  
Deep Learning ◽  
Extreme Weather ◽  
Extreme Weather Events ◽  
Weather Events ◽  
Forecasting Method ◽  
Learning Technique

New deep learning technique brings an obsolete forecasting method “back to life” to predict extreme weather events.

The Molecular Farm

2020 ◽  
pp. 133-155
Author(s):  
John Parrington
Keyword(s):  
Adverse Effect ◽  
Global Warming ◽  
Adverse Effects ◽  
Animal Welfare ◽  
Genome Editing ◽  
Extreme Weather ◽  
Animal Production ◽  
Weather Patterns ◽  
Modern Agriculture ◽  
The World

Despite many inequalities in the world, it is a testament to human technology that modern agriculture is able to feed the 8 billion people on the planet. However, recently extreme weather patterns linked to global warming have been having an adverse effect on crops and farmed animal production, leading to fears about whether agriculture can continue to feed all the humans on the planet. Genome editing looks set to revolutionise agriculture by making it possible to precisely edit the genomes of farm plants and animals rapidly and economically in an unprecedented way. Such editing could be used to create vegetables and meat with enhanced flavour or nutrition. It could also be used to create disease resistant plants and animals, and reduce the use of antibiotics or pesticides. Looking further into the future it might eventually be possible to use genome editing to reconfigure plants or animals to survive in increasingly extreme types of climates. Despite these positive ways of using genome editing in agriculture, concerns have been raised about the safety of food produced from genome edited animals and plants, and potential adverse effects on animal welfare. Another criticism is that genome editing may only benefit giant agribusiness companies, and not ordinary farmers and consumers. Yet against this criticism, one of the revolutionary aspects of genome editing is how easy and economical it is to use, which means that unlike previous GM technologies, there is no reason why it cannot be used in a local, sustainable, and accessible way.

Weather associated with the start of mountain pine beetle outbreaks

1984 ◽  
Vol 14 (2) ◽  
pp. 255-258 ◽  
Author(s):  
A. J. Thomson ◽  
D. M. Shrimpton
Keyword(s):  
Tree Growth ◽  
Mountain Pine Beetle ◽  
Weather Conditions ◽  
Extreme Weather ◽  
Growth Rings ◽  
Noticeable Effect ◽  
Weather Patterns ◽  
Mountain Pine ◽  
Annual Growth Rings ◽  
Pine Beetle

Extreme weather conditions associated with mountain pine beetle outbreaks were evaluated by graphical techniques for six locations throughout British Columbia. Three major associations of extreme weather patterns with lodgepole pine growth and mountain pine beetle outbreaks were identified. (i) Weather effects prior to, or early in, the growing season can reduce growth without releasing the beetle population. (ii) Weather conducive to beetle establishment and early brood development can occur too late in the season to have a noticeable effect on tree growth and therefore will not be recorded in the annual growth rings. (iii) Warm, dry periods during the summer are associated with tree growth reduction and the beginnings of outbreaks. In each of these three cases, extreme low precipitation levels were involved. Average precipitation in some months did not compensate for the effects of unfavourable extremes in other months on tree growth.

scholarly journals Analog forecasting of extreme-causing weather patterns using deep learning

2019 ◽  
Author(s):  
Ashesh Chattopadhyay ◽  
Pedram Hassanzadeh ◽  
Ebrahim Nabizadeh
Keyword(s):  
Deep Learning ◽  
Weather Patterns

scholarly journals ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather

2021 ◽  
Vol 14 (1) ◽  
pp. 107-124
Author(s):  
◽  
Karthik Kashinath ◽  
Mayur Mudigonda ◽  
Sol Kim ◽  
Lukas Kapp-Schwoerer ◽  
...  
Keyword(s):  
Climate Change ◽  
Deep Learning ◽  
Climate Model ◽  
Extreme Weather ◽  
Training Data ◽  
Extreme Weather Events ◽  
Climate Change Scenarios ◽  
Model Output ◽  
Weather And Climate ◽  
Climate Model Output

Abstract. Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning – when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create “ClimateNet” – an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification – i.e., segmentation – of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs, or “the background” at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, high-fidelity, and highly precise analytics of climate data using a curated expert-labeled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning.

scholarly journals Analog Forecasting of Extreme‐Causing Weather Patterns Using Deep Learning

2020 ◽  
Vol 12 (2) ◽  
Author(s):  
Ashesh Chattopadhyay ◽  
Ebrahim Nabizadeh ◽  
Pedram Hassanzadeh
Keyword(s):  
Deep Learning ◽  
Weather Patterns

scholarly journals Climate Change and Emerging Food Safety Issues

2021 ◽  
Author(s):  
Ramona A. Duchenne-Moutien ◽  
Hudaa Neetoo
Keyword(s):  
Climate Change ◽  
Heavy Metals ◽  
Food Safety ◽  
Climate Variability ◽  
Extreme Weather ◽  
Cold Chain ◽  
Extreme Weather Events ◽  
Global Issues ◽  
Weather Patterns ◽  
Weather Events

Throughout these past decades, climate change has featured among one of the most complex global issues. Characterized by worldwide alterations in weather patterns, along with a concomitant increase in the temperature of the Earth, climate change will undoubtedly have significant effects on food security and food safety. Climate change engenders climate variability, which are significant variations in weather variables and in their frequency. Both climate variability and climate change are thought to threaten the safety of the food supply chain through different pathways. One such pathway is their ability to exacerbate foodborne diseases by influencing the occurrence, persistence, virulence and, in some cases, toxicity of certain groups of disease-causing microorganisms. Food safety can also be compromised by various chemical hazards such as pesticides, mycotoxins and heavy metals. With changes in weather patterns such as lower rainfall, higher air temperature and higher frequency of extreme weather events amongst others, this translates to emerging food safety concerns. These include shortage of safe water for irrigation of agricultural produce, greater use of pesticides due to pest resistance, increased difficulty in achieving a well-controlled cold chain resulting in temperature abuse, or occurrence of flash floods which cause run-off of chemical contaminants in natural water courses. Together, these can result in foodborne infection, intoxication, antimicrobial resistance and long-term bioaccumulation of chemicals and heavy metals in the human body. Furthermore, severe climate variability can result in extreme weather events and natural calamities, which directly or indirectly impair food safety. This review discusses the causes and impacts of climate change and variability on existing as well as emerging food safety risks, and also considers mitigation and adaptation strategies to address the global warming and climate change problem.

Extreme Weather Prediction Using 2-Phase Deep Learning Pipeline

2020 ◽  
pp. 266-282
Author(s):  
Vidhey Oza ◽  
Yash Thesia ◽  
Dhananjay Rasalia ◽  
Priyank Thakkar ◽  
Nitant Dube ◽  
...  
Keyword(s):  
Deep Learning ◽  
Weather Prediction ◽  
Extreme Weather
Sign in / Sign up

Export Citation Format

Share Document