A review of Earth Artificial Intelligence

Computers & Geosciences, Journal Year: 2022, Volume and Issue: 159, P. 105034 - 105034

Published: Jan. 5, 2022

In recent years, Earth system sciences are urgently calling for innovation on improving accuracy, enhancing model intelligence level, scaling up operation, and reducing costs in many subdomains amid the exponentially accumulated datasets promising artificial (AI) revolution computer science. This paper presents work led by NASA Science Data Systems Working Groups ESIP machine learning cluster to give a comprehensive overview of AI sciences. It holistically introduces current status, technology, use cases, challenges, opportunities, provides all levels practitioners geosciences with an overall big picture "blow away fog get clearer vision" about future development AI. The covers majorspheres investigates representative research each domain. Widely used algorithms computing cyberinfrastructure briefly introduced. mandatory steps typical workflow specializing solve scientific problems decomposed analyzed. Eventually, it concludes grand challenges reveals opportunities some guidance pre-warnings allocating resources wisely achieve ambitious goals future.

Language: Английский

---

Soil Salinity Mapping Using Machine Learning Algorithms with the Sentinel-2 MSI in Arid Areas, China

Remote Sensing, Journal Year: 2021, Volume and Issue: 13(2), P. 305 - 305

Published: Jan. 17, 2021

Accurate monitoring of soil salinization plays a key role in the ecological security and sustainable agricultural development arid regions. As branch artificial intelligence, machine learning acquires new knowledge through self-learning continuously improves its own performance. The purpose this study is to combine Sentinel-2 Multispectral Imager (MSI) data MSI-derived covariates with measured salinity apply three algorithms modeling estimate map sample area. According convenient transportation conditions, area sampling quadrat were set up, 5-point method was used collect mixed samples, 160 samples collected. Kennard–Stone (K–S) algorithm for classification, 70% 30% verification. uses Support Vector Machines (SVM), Artificial Neural Network (ANN), Random Forest (RF). results showed that (1) average reflectance each band MSI ranged from 0.21–0.28. spectral characteristics corresponding different electrical conductivity (EC) levels (1.07–79.6 dS m−1), salinized 0.09–0.35. (2) correlation coefficient between EC moderate, certain sets not significant. (3) SVM estimation model established attained higher performance accuracy (R2 = 0.88, root mean square error (RMSE) 4.89 m−1, ratio interquartile range (RPIQ) 1.96, standard laboratory measurements predictions (SEL/SEP) 1.11) than those models RF ANN models. (4) We applied area, which farmland altitudes discharged large amount salt surroundings due long-term irrigation, secondary also caused accumulation. This research provides scientific basis simulation scenarios areas future.

Language: Английский

---

A new application of deep neural network (LSTM) and RUSLE models in soil erosion prediction

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 845, P. 157220 - 157220

Published: July 12, 2022

Language: Английский

---

Evaluation of machine learning algorithms for groundwater quality modeling

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(16), P. 46004 - 46021

Published: Jan. 30, 2023

Language: Английский

---

Spatial–temporal evolution patterns of soil erosion in the Yellow River Basin from 1990 to 2015: impacts of natural factors and land use change

Geomatics Natural Hazards and Risk, Journal Year: 2020, Volume and Issue: 12(1), P. 103 - 122

Published: Dec. 24, 2020

This study optimized the slope and length factor (LS) crop management (P) of RUSLE model then introduced gravity centre to analyze spatial–temporal variation patterns soil erosion in Yellow River Basin from a new perspective. Results showed that: (1) The improved with factors LS P had better applicability Basin; (2) average intensity was 2777.5 t/a, which belonged moderate erosion. an overall trend increasing firstly (1990–2005) decreasing (2005–2015). (3) During 1990–2015, moved southwest, indicating that increment rate southwest parts were greater than northeast parts. (4) aggravated slope. sandy soil, chestnut light-grey calcium fluvo aquic severe due regional climate their own physical–chemical structure. woodland shrubbery land more susceptible

Language: Английский

---

Hybrid Machine Learning Approach for Gully Erosion Mapping Susceptibility at a Watershed Scale

ISPRS International Journal of Geo-Information, Journal Year: 2022, Volume and Issue: 11(7), P. 401 - 401

Published: July 14, 2022

Gully erosion is a serious threat to the state of ecosystems all around world. As result, safeguarding soil for our own benefit and from actions must guaranteeing long-term viability variety ecosystem services. developing gully susceptibility maps (GESM) both suggested necessary. In this study, we compared effectiveness three hybrid machine learning (ML) algorithms with bivariate statistical index frequency ratio (FR), named random forest-frequency (RF-FR), support vector machine-frequency (SVM-FR), naïve Bayes-frequency (NB-FR), in mapping GHISS watershed northern part Morocco. The models were implemented based on inventory total number 178 points randomly divided into 2 groups (70% used training 30% validation process), 12 conditioning variables (i.e., elevation, slope, aspect, plane curvature, topographic moisture (TWI), stream power (SPI), precipitation, distance road, stream, drainage density, land use, lithology). Using equal interval reclassification method, spatial distribution was categorized five different classes, including very high, moderate, low, low. Our results showed that high classes derived using RF-FR, SVM-FR, NB-FR covered 25.98%, 22.62%, 27.10% area, respectively. area under receiver (AUC) operating characteristic curve, precision, accuracy employed evaluate performance these models. Based (ROC), RF-FR achieved best (AUC = 0.91), followed by SVM-FR 0.87), then 0.82), contribution, line Sustainable Development Goals (SDGs), plays crucial role understanding identifying issue “where why” occurs, hence it can serve as first pathway reducing particular area.

Language: Английский

---

Mapping of Water-Induced Soil Erosion Using Machine Learning Models: A Case Study of Oum Er Rbia Basin (Morocco)

Earth Systems and Environment, Journal Year: 2022, Volume and Issue: 7(1), P. 151 - 170

Published: June 12, 2022

Language: Английский

---

Predicting soil erosion susceptibility associated with climate change scenarios in the Central Highlands of Sri Lanka

Journal of Environmental Management, Journal Year: 2022, Volume and Issue: 308, P. 114589 - 114589

Published: Feb. 2, 2022

Language: Английский

---

Spatio-temporal variation in soil erosion on sloping farmland based on the integrated valuation of ecosystem services and trade-offs model: A case study of Chongqing, southwest China

CATENA, Journal Year: 2023, Volume and Issue: 236, P. 107693 - 107693

Published: Nov. 27, 2023

Language: Английский

---

Spatial distribution and driving factors of soil organic carbon in the Northeast China Plain: Insights from latest monitoring data

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 911, P. 168602 - 168602

Published: Nov. 14, 2023

Language: Английский

---