Artificial intelligence: A powerful paradigm for scientific research

The Innovation, Journal Year: 2021, Volume and Issue: 2(4), P. 100179 - 100179

Published: Oct. 29, 2021

•"Can machines think?" The goal of artificial intelligence (AI) is to enable mimic human thoughts and behaviors, including learning, reasoning, predicting, so on.•"Can AI do fundamental research?" coupled with machine learning techniques impacting a wide range sciences, mathematics, medical science, physics, etc.•"How does accelerate New research applications are emerging rapidly the support by infrastructure, data storage, computing power, algorithms, frameworks. Artificial promising (ML) well known from computer science broadly affecting many aspects various fields technology, industry, even our day-to-day life. ML have been developed analyze high-throughput view obtaining useful insights, categorizing, making evidence-based decisions in novel ways, which will promote growth fuel sustainable booming AI. This paper undertakes comprehensive survey on development application different information materials geoscience, life chemistry. challenges that each discipline meets, potentials handle these challenges, discussed detail. Moreover, we shed light new trends entailing integration into scientific discipline. aim this provide broad guideline sciences potential infusion AI, help motivate researchers deeply understand state-of-the-art AI-based thereby continuous sciences.

Language: Английский

---

Recent Advances of Hyperspectral Imaging Technology and Applications in Agriculture

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(16), P. 2659 - 2659

Published: Aug. 18, 2020

Remote sensing is a useful tool for monitoring spatio-temporal variations of crop morphological and physiological status supporting practices in precision farming. In comparison with multispectral imaging, hyperspectral imaging more advanced technique that capable acquiring detailed spectral response target features. Due to limited accessibility outside the scientific community, images have not been widely used agriculture. recent years, different mini-sized low-cost airborne sensors (e.g., Headwall Micro-Hyperspec, Cubert UHD 185-Firefly) developed, spaceborne also or will be launched PRISMA, DESIS, EnMAP, HyspIRI). Hyperspectral becoming available agricultural applications. Meanwhile, acquisition, processing, analysis imagery still remain challenging research topic large data volume, high dimensionality, complex information analysis). It hence beneficial conduct thorough in-depth review technology platforms sensors), methods processing analyzing information, advances Publications over past 30 years applications agriculture were thus reviewed. The sensors, together analytic literature, discussed. Performances biophysical biochemical properties’ mapping, soil characteristics, classification) evaluated. This intended assist researchers practitioners better understand strengths limitations promote adoption this valuable technology. Recommendations future are presented.

Language: Английский

---

A review on deep learning in UAV remote sensing

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2021, Volume and Issue: 102, P. 102456 - 102456

Published: July 27, 2021

Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural language, audio, video, many others. In the remote sensing field, surveys literature revisions specifically involving DNNs algorithms' applications have been conducted in attempt to summarize amount of information produced its subfields. Recently, Unmanned Aerial Vehicle (UAV)-based dominated aerial research. However, a revision that combines both "deep learning" "UAV sensing" thematics has not yet conducted. The motivation our work was present comprehensive review fundamentals Learning (DL) applied UAV-based imagery. We focused mainly on describing classification regression techniques used recent UAV-acquired data. For that, total 232 papers published international scientific journal databases examined. gathered materials evaluated their characteristics regarding application, sensor, technique used. discuss how DL presents promising results potential tasks associated image Lastly, we project future perspectives, commentating prominent paths be explored UAV field. This consisting approach introduce, commentate, state-of-the-art algorithms diverse subfields sensing, grouping it environmental, urban, agricultural contexts.

Language: Английский

---

Artificial Intelligence for Remote Sensing Data Analysis: A review of challenges and opportunities

IEEE Geoscience and Remote Sensing Magazine, Journal Year: 2022, Volume and Issue: 10(2), P. 270 - 294

Published: April 13, 2022

Artificial intelligence (AI) plays a growing role in remote sensing (RS). Applications of AI, particularly machine learning algorithms, range from initial image processing to high-level data understanding and knowledge discovery. AI techniques have emerged as powerful strategy for analyzing RS led remarkable breakthroughs all fields. Given this period breathtaking evolution, work aims provide comprehensive review the recent achievements algorithms applications analysis. The includes more than 270 research papers, covering following major aspects innovation RS: learning, computational intelligence, explicability, mining, natural language (NLP), security. We conclude by identifying promising directions future research.

Language: Английский

---

Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 299, P. 113856 - 113856

Published: Oct. 29, 2023

Language: Английский

---

High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2020, Volume and Issue: 92, P. 102163 - 102163

Published: June 6, 2020

Forest canopy height is an important indicator of forest carbon storage, productivity, and biodiversity. The present study showed the first attempt to develop a machine-learning workflow map spatial pattern in mountainous region northeast China by coupling recently available (Hcanopy) footprint product from ICESat-2 with Sentinel-1 Sentinel-2 satellite data. Hcanopy was initially validated high-resolution airborne LiDAR data at different scales. Performance comparisons were conducted between two models – deep learning (DL) model random (RF) model, Sentinel Landsat-8 satellites. Results that highest correlation scale 250 m Pearson's coefficient (R) 0.82 mean bias -1.46 m, providing evidence on reliability vegetation case China's forest. Both DL RF obtained satisfactory accuracy upscaling assisted co-variables R-value observed predicted equalling 0.78 0.68, respectively. Compared satellites, relatively weaker performance prediction, suggesting addition backscattering coefficients red-edge related variables could positively contribute prediction height. To our knowledge, few studies have demonstrated large-scale mapping resolution ≤ based newly satellites (ICESat-2, Sentinel-2) regression particularly areas China. Thus, work provided timely supplementary applications these new earth observation tools.

Language: Английский

---

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 63406 - 63439

Published: Jan. 1, 2021

An early and reliable estimation of crop yield is essential in quantitative financial evaluation at the field level for determining strategic plans agricultural commodities import-export policies doubling farmer's incomes. Crop predictions are carried out to estimate higher through use machine learning algorithms which one challenging issues sector. Due this developing significance prediction, article provides an exhaustive review on predict with special emphasis palm oil prediction. Initially, current status around world presented, along a brief discussion overview widely used features prediction algorithms. Then, critical state-of-the-art learning-based application industry comparative analysis related studies presented. Consequently, detailed study advantages difficulties proper identification future challenges The potential solutions additionally prescribed order alleviate existing problems Since major objectives explore perspectives areas including remote sensing, plant's growth disease recognition, mapping tree counting, optimum have been broadly discussed. Finally, prospective architecture has proposed based studies. This technology will fulfill its promise by performing new research development extremely effective model yields most minimal computational difficulty.

Language: Английский

---

Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(13), P. 2450 - 2450

Published: June 23, 2021

Convolutional neural network (CNN)-based deep learning (DL) is a powerful, recently developed image classification approach. With origins in the computer vision and processing communities, accuracy assessment methods for CNN-based DL use wide range of metrics that may be unfamiliar to remote sensing (RS) community. To explore differences between traditional RS methods, we surveyed random selection 100 papers from literature. The results show studies have largely abandoned terminology, though some measures typically used papers, most notably precision recall, direct equivalents terminology. Some terms multiple names, or are equivalent another measure. In our sample, only rarely reported complete confusion matrix, when they did so, it was even more rare matrix estimated population properties. On other hand, increasingly paying attention role class prevalence designing approaches. evaluate decision boundary threshold over values tend precision-recall (P-R) curve, associated area under curve (AUC) average (AP) mean (mAP), rather than receiver operating characteristic (ROC) its AUC. also notable testing generalization their models on entirely new datasets, including data areas, acquisition times, sensors.

Language: Английский

---

Deep learning for geological hazards analysis: Data, models, applications, and opportunities

Earth-Science Reviews, Journal Year: 2021, Volume and Issue: 223, P. 103858 - 103858

Published: Nov. 8, 2021

As natural disasters are induced by geodynamic activities or abnormal changes in the environment, geological hazards tend to wreak havoc on environment and human society. Recently, dramatic increase volume of various types Earth observation 'big data' from multiple sources, rapid development deep learning as a state-of-the-art data analysis tool, have enabled novel advances hazard analysis, with ultimate aim mitigate devastation associated these hazards. Motivated numerous applications, this paper presents an overview utilization for analysis. First, six commonly available sources described, e.g., unmanned aerial vehicles, satellite platforms, in-situ monitoring systems. Second, background typical models introduced, such convolutional neural networks recurrent networks. Third, focusing hazards, i.e., landslides, debris flows, rockfalls, avalanches, earthquakes, volcanoes, applications reviewed, common application paradigms summarized. Finally, challenges opportunities highlighted, inspire further related research.

Language: Английский

---

High-quality vegetation index product generation: A review of NDVI time series reconstruction techniques

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2021, Volume and Issue: 105, P. 102640 - 102640

Published: Dec. 1, 2021

Normalized difference vegetation index (NDVI) derived from satellites has been ubiquitously utilized in the field of remote sensing. Nevertheless, there are multitudinous contaminations NDVI time series because atmospheric disturbance, cloud cover, sensor failure, and so on. It is crucial to remove noises prior further applications. Numerous techniques have proposed alleviate this issue last few decades. To best our knowledge, hasn't a systematical study summarize analyze status reconstruction since 1980s. As result, goal recapitulate current approaches for reconstructing high-quality series, followed by an interpretation on principle, merits demerits different kinds methods. They were mainly classified into temporal-based methods, frequency-based methods hybrid The evaluation quality introduced, accompanied with future development tendency.

Language: Английский

---