Reinforcement learning (RL) algorithms have shown impressive success in exploring high-dimensional environments to learn complex, long-horizon tasks, but can often exhibit unsafe behaviors and require extensive environment interaction when exploration is unconstrained. A promising strategy for safe learning in dynamically uncertain environments is requiring that the agent can robustly return to states where task success (and therefore safety) can be guaranteed. While this approach has been successful in low-dimensions, enforcing this constraint in environments with high-dimensional state spaces, such as images, is challenging. We present Latent Space Safe Sets (LS3), which extends this strategy to iterative, long-horizon tasks with image observations by using suboptimal demonstrations and a learned dynamics model to restrict exploration to the neighborhood of a learned Safe Set where task completion is likely. We evaluate LS3 on 4 domains, including a challenging sequential pushing task in simulation and a physical cable routing task. We find that LS3 can use prior task successes to restrict exploration and learn more efficiently than prior algorithms while satisfying constraints. See https://tinyurl.com/latent-ss for code and supplementary material.

Recent advancements in artificial neural networks that focus on reconstructing 3D meshes from input 2D images show great potential and significant practical value in a multitude of GIS applications. This series of posts describes our experiments with one such neural network architecture that we applied to reconstruct 3D building shells from various types of remotely sensed data. This post, the first of the series, describes extracting buildings from elevation rasters, specifically, normalized digital surface model rasters. Modern municipal governments and national mapping agencies are evolving their traditional 2D geographic datasets into 3D interactive and realistically looking digital twins to optimize results from planning an analysis projects. For example, some local governments that are responsible for urban design, public events planning, safety, pollution monitoring, solar radiation potential assessment, etc. rely more and more on this kind of data.

Artificial Intelligence Technologies and Sustainability of Our Environment Taniya Basu Wed, 07/07/2021 – 21:01 Log in or register to post comments Introduction: In recent years, the environmental issues have triggered debates, discussions, awareness programs and public outrage that have catapulted interest in new technologies, such as Artificial Intelligence. Artificial Intelligence finds application in environmental sectors, including natural resource conservation, wildlife protection, energy management, clean energy, waste management, pollution control and agriculture. Advancement in the AI in environmental protection market could be one of the solutions to solve the major environmental concerns. The application of AI in environment protection includes machine learning for protecting the oceans, monitoring shipping, ocean mining, fishing, coral bleaching or the outbreak of marine disease. The AI techniques are quite beneficial for environmental analysis, as they are able to process a huge amount of data quickly so as to draw conclusions that may have not been possible by humans. The AI techniques are quite beneficial for environmental analysis, as they are able to process a huge amount of data quickly so as to draw conclusions that may have not been possible by humans.  1.Weather Forecasting & Climate Changes: The traditional models of weather forecasting are based on statistical measures of numeric models, and it does not give answers in binary. The data collected can be from deep space satellites, weather balloons, radar systems, nowcasting weather warnings and environmental analytics and sometimes from IoT based sensors.  The AI predictions are primarily based on machine learning algorithms. By processing more complex data in a shorter span of time using linear regression principles, now meteorologists can make predictions with improved accuracy and thus saves lives and money. Machine learning can abet with other forecasts as well, including temperature, wave height, and precipitation. Google’s AI forecast tool that is based on the UNET convolutional neural network (CNN) allows researchers to generate accurate rainfall predictions six hours ahead of when the precipitation occurs. CNN is a sequence of layers of mathematical operations arranged in an encoding phase. It takes the input satellite imagery and then transforms them into output images. 2.Climate Changes: For instance, we can halt emissions in the energy sector by using AI technology to forecast the supply and demand of power in the grid, improve the scheduling renewables, and reduce the life-cycle fossil fuel emissions through predictive maintenance. AI applications in transportation can enable more accurate traffic predictions, the development of freight transportation, and better modelling of demand and shared mobility option. Other kinds of impacts include the waste that is disrupting ecosystems, pollutants that affect human and animal health and biodiversity loss. By harnessing the swaths of data from sensors and satellites, we can better predict climate change impacts and proactively steward these ecosystems.  AI applied in food systems can help better monitor crop yields, reduce the need for chemicals and excess water through precision agriculture and minimize food waste through forecasting demand and identifying spoiled produce. Lastly, AI systems used in buildings and cities can help automatically control heating and cooling as well as model energy used to decide which buildings to retrofit.  3.Biodiversity and Conservation: With the recent development of AI-powered devices for the conservation of animals, we can now prevent wildlife extinction. After the extinction of western African rhinoceros, African elephants are next on the verge of going extinct due to the involvement of extensive poaching. The AI-based technology system uses a camera that detects poachers planning to attack an animal and subsequently generates an alert to the park rangers in real Plants are very beneficial for human lives and greatly help in fulfilling our necessities. They help fulfill our basic necessities as they can provide us with food, shelter, and medicine. The more the number of trees present in an environment, the greater is the amount of oxygen produced. The AI-based platform allows its users to click and share photos of various species of plants in real time. It also allows the other community members to identify the photos of the specific plant and confirm the plant’s presence, whether if such a plant already exists. In this way, the AI-based networking platform can help discover new species of plants worldwide. 4.Ocean Health: In a recent research by two AI algorithm— Latent Variable Gaussian Process (LVGP) model and Probabilistic Principal Component Analysis (PPCA) were used to understand the sonar echoes in the ocean. The research aimed at observing the changes that can happen with sonar echoes at different depths, salinity, and temperature. The algorithms were capable of classifying underwater environments from simulated sonar measurements with an average accuracy of more than 90%.  The application of artificial intelligence, ML algorithms, and smart robots seems to be the perfect combination in the future to come. Deep-sea mining and deep-sea research without disturbing the life beneath seem difficult a few years before, but not anymore. With the application of these latest technologies, oceanographers can create accurate cartography, understand the impact of climate change, species status, salinity, and gather a large amount of data to explore the areas left behind. Conclusion: Researchers and scientists must ensure that the data provided through Artificial Intelligence systems are transparent, fair and trustworthy. With an increasing demand of automation solutions and higher precision data-study for environment related problems and challenges, more multinational companies, educational institutions and government sectors need to fund more R&D of such technologies and provide proper standardizations for producing and applying them. In addition, there is a necessity to bring in more technologists and developers to this technology. Artificial intelligence is steadily becoming a part in our daily lives, and its impact can be seen through the advancements made in the field of environmental sciences and environmental management. Attachment AI IN ENVIRONMENT TECH.pdf Cover Image Image Publish Location Tech for Good

A research team at the University of Córdoba has developed and evaluated models for the prediction of solar radiation in nine locations in southern Spain and North Carolina (USA). Measuring solar radiation is costly, as are all the tasks related to the maintenance and calibration of the most commonly used sensors: pyranometers and radiometers. The result is a paucity of reliable data. Hence, a research group from the University of Córdoba has developed and evaluated several Machine Learning models to predict solar radiation in nine locations (southern Spain and North Carolina, USA) spanning a range of different geo-climatic conditions (aridity, distance to the sea, and elevation). The work has been featured in the journal Applied Energy.

A research team at the University of Córdoba has developed and evaluated models for the prediction of solar radiation in nine locations in southern Spain and North Carolina (USA). Measuring solar radiation is costly, as are all the tasks related to the maintenance and calibration of the most commonly used sensors: pyranometers and radiometers. The result is a paucity of reliable data. Hence, a research group from the University of Córdoba has developed and evaluated several Machine Learning models to predict solar radiation in nine locations (southern Spain and North Carolina, USA) spanning a range of different geo-climatic conditions (aridity, distance to the sea, and elevation). The work has been featured in the journal Applied Energy.

To tackle climate change, scientists and advocates have called for a bevy of actions that include reducing fossil fuel use, electrifying transportation, reforming agriculture, and mopping up excess carbon dioxide from the atmosphere. But many of these challenges will be insurmountable without behind-the-scenes breakthroughs in materials science. Today's materials lack key properties needed for scalable climate-friendly technologies. Batteries, for example, require improved materials that can yield higher energy densities and longer discharge times. Without such improvements, commercial batteries won't be able to power mass-market electric vehicles and support a renewable-powered grid.

According to AIMResearch, Indian AI startups raised $836.3 million in 2020, the largest funding outlay in the last seven years at a 9.7% year-on-year growth. The same year, Indian government increased the outlay for Digital India to $477 million to boost AI, IoT, big data, cybersecurity, machine learning and robotics. In the 2019 Union Budget, Finance Minister Nirmala Sitharaman said the government would offer industry-relevant skill training for 10 million youth in India in technologies like AI, Big Data and robotics. To wit, India's AI ecosystem is seeing explosive growth with a lot of inventive startups entering the space. Analytics India Magazine comes with a list of 10 exceptional startups leading the AI race every year.

Elon Musk has expressed worry about the advent of a digital superintelligent AI numerous times now. He has put solid solutions to the AI control problem. One of which is the merging scenario with AI. But first Elon Musk, is focused on making sure humanity makes the transition to renewable energy, which is the first right step towards becoming a type 1 civilization.

Climate change, increasing populations, competing demands on land for production of biofuels and declining soil quality are challenging global food security. Finding sustainable solutions requires bold new approaches and integration of knowledge from diverse fields, such as materials science and informatics. The convergence of precision agriculture, in which farmers respond in real time to changes in crop growth with nanotechnology and artificial intelligence, offers exciting opportunities for sustainable food production. Coupling existing models for nutrient cycling and crop productivity with nanoinformatics approaches to optimize targeting, uptake, delivery, nutrient capture and long-term impacts on soil microbial communities will enable design of nanoscale agrochemicals that combine optimal safety and functionality profiles. This Perspective discusses the applications of nanotechnology and artificial intelligence in agriculture, highlighting the opportunities and challenges of using these technologies to achieve sustainable and precision agriculture.

This paper aims to improve the reliability of optimal control using models constructed by machine learning methods. Optimal control problems based on such models are generally non-convex and difficult to solve online. In this paper, we propose a model that combines the Hammerstein-Wiener model with input convex neural networks, which have recently been proposed in the field of machine learning. An important feature of the proposed model is that resulting optimal control problems are effectively solvable exploiting their convexity and partial linearity while retaining flexible modeling ability. The practical usefulness of the method is examined through its application to the modeling and control of an engine airpath system.