Deep learning in environmental remote sensing: Achievements and challenges

https://lms.ctl.cyut.edu.tw/sys/read_attach.php?id=2718322

An ANN application for water quality forecasting.

Artificial intelligence based models for stream-flow forecasting: 2000–2015

[1] Comets, planetary rings, exposed dusty surfaces, and the zodiacal dust cloud are all examples of environments where dusty plasma effects establish the size and spatial distributions of small grains. Simultaneously, dust often influences the composition, density, and temperature of the plasma surrounding it. The dynamics of charged dust particles can be surprisingly complex and fundamentally different from the well-understood limits of gravitationally dominated motions of neutral particles or the adiabatic motion of electrons and ions in electromagnetic fields that dominate gravity. In this review we focus on observations that are best explained by theories concerning dusty plasma effects at Saturn. In addition to presenting our current models we also discuss our expectations for new discoveries based on existing observations at Jupiter or on purely theoretical considerations. Our intent is to give an up-to-date overview of dusty plasma effects in Saturn's magnetosphere and to draw attention to several outstanding problems that could be resolved by the Cassini mission.

Dusty plasma effects in Saturn's magnetosphere

Advances in Earth Observation (EO) technology, particularly over the last two decades, have shown that soil moisture content (SMC) can be measured to some degree or other by all regions of the electromagnetic spectrum, and a variety of techniques have been proposed to facilitate this purpose.

In this review we provide a synthesis of the efforts made during the last 20 years or so towards the estimation of surface SMC exploiting EO imagery, with a particular emphasis on retrievals from microwave sensors. Rather than replicating previous overview works, we provide a comprehensive and critical exploration of all the major approaches employed for retrieving SMC in a range of different global ecosystems. In this framework, we consider the newest techniques developed within optical and thermal infrared remote sensing, active and passive microwave domains, as well as assimilation or synergistic approaches. Future trends and prospects of EO for the accurate determination of SMC from space are subject to key challenges, some of which are identified and discussed within.

It is evident from this review that there is potential for more accurate estimation of SMC exploiting EO technology, particularly so, by exploring the use of synergistic approaches between a variety of EO instruments. Given the importance of SMC in Earth’s land surface interactions and to a large range of applications, one can appreciate that its accurate estimation is critical in addressing key scientific and practical challenges in today’s world such as food security, sustainable planning and management of water resources. The launch of new, more sophisticated satellites strengthens the development of innovative research approaches and scientific inventions that will result in a range of pioneering and ground-breaking advancements in the retrievals of soil moisture from space.

Surface soil moisture retrievals from remote sensing: Current status, products & future trends

Improving wave predictions with artificial neural networks

Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks

Artificial neural networks in wave predictions at the west coast of Portugal

In the present study, the artificial intelligence meshless methodology of neural networks was used to predict hourly sea level variations for the following 24 h, as well as for half-daily, daily, 5-daily and 10-daily mean sea levels. The methodology is site specific; therefore, as an example, the measurements from a single tide gauge at Hillarys Boat Harbour, Western Australia, for the period December 1991–December 2002 were used to train and to validate the employed neural networks. The results obtained show the feasibility of the neural sea level forecasts in terms of the correlation coefficient (0.7–0.9), root mean square error (about 10% of tidal range) and scatter index (0.1–0.2).

/pdf/predicting-sea-level-variations-with-artificial-neural-4t1vzl0cnn.pdf

Oleg Makarynskyy

Papers

Improving wave predictions with artificial neural networks

Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks

Artificial neural networks in wave predictions at the west coast of Portugal

Predicting sea level variations with artificial neural networks at Hillarys Boat Harbour, Western Australia

Neuro-fuzzy and neural network techniques for forecasting sea level in Darwin Harbor, Australia