Advancing SDGs: Predicting Future Shifts in Saudi Arabia’s Terrestrial Water Storage Using Multi-Step-Ahead Machine Learning Based on GRACE Data

Water, Journal Year: 2024, Volume and Issue: 16(2), P. 246 - 246

Published: Jan. 11, 2024

The availability of water is crucial for the growth and sustainability human development. effective management resources essential due to their renewable nature critical role in ensuring food security safety. In this study, multi-step-ahead modeling approach Gravity Recovery Climate Experiment (GRACE) terrestrial storage (TWS) was utilized gain insights into forecast fluctuations within Saudi Arabia. This study conducted using mascon solutions obtained from University Texas Center Space Research (UT-CSR) over period 2007 2017. data were used development artificial intelligence models, namely, an Elman neural network (ENN), a backpropagation (BPNN), kernel support vector regression (k-SVR). These models constructed various input variables, such as t-12, t-24, t-36, t-48, TWS, with output variable being focus. A simple weighted average ensemble introduced improve accuracy marginal weak predictive results. performance assessed use several evaluation metrics, including mean absolute error (MAE), root square (RMSE), percentage (MAPE), correlation coefficient (CC), Nash–Sutcliffe efficiency (NSE). results estimate indicate that k-SVR-M1 (NSE = 0.993, MAE 0.0346) produced favorable outcomes, whereas ENN-M3 0.6586, 0.6895) emerged second most model. combinations all other exhibited accuracies ranging excellent marginal, rendering them unreliable decision-making purposes. Error methods improved standalone model proved merit. also serve important tool monitoring changes global resources, aiding drought management, understanding Earth’s cycle.

Language: Английский

---

Assessing the performance of the Gaussian Process Regression algorithm to fill gaps in the time-series of daily actual evapotranspiration of different crops in temperate and continental zones using ground and remotely sensed data

Agricultural Water Management, Journal Year: 2023, Volume and Issue: 290, P. 108596 - 108596

Published: Nov. 18, 2023

The knowledge of crop evapotranspiration is crucial for several hydrological processes, including those related to the management agricultural water sources. In particular, estimations actual fluxes within fields are essential managing irrigation strategies save and preserve resources. Among indirect methods estimate evapotranspiration, ETa, eddy covariance (EC) method allows acquire continuous measurement latent heat flux (LE). However, time series EC measurements sometimes characterized by a lack data due sensors' malfunctions. At this aim, Machine Learning (ML) techniques could represent powerful tool fill possible gaps in series. paper, ML technique was applied using Gaussian Process Regression (GPR) algorithm daily evapotranspiration. tested six different plots, two Italy, three United States America, one Canada, with crops climatic conditions order consider suitability model various contexts. For each site, climate variables were not same, therefore, performance investigated on basis available information. Initially, comparison ground reanalysis data, where both databases available, between satellite products, when have been conducted. Then, GPR tested. mean functions set considering database variables, soil status measurements, remotely sensed vegetation indices. five combinations analyzed verify approach limited input or weather replaced data. Cross-validation used assess procedure. performances assessed based statistical indicators: Root Mean Square Error (RMSE), coefficient determination (R2), Absolute (MAE), regression (b), Nash-Sutcliffe efficiency (NSE). quite high Nash Sutcliffe Efficiency (NSE) coefficient, root square error (RMSE) low values confirm proposed algorithm.

Language: Английский

---

Quantifying effects of climate change and farmers' information demand on wheat yield in India: a deep learning approach with regional clustering

Frontiers in Sustainable Food Systems, Journal Year: 2024, Volume and Issue: 8

Published: May 31, 2024

Introduction With increasing demand for food and changing environmental conditions, a better understanding of the factors impacting wheat yield is essential ensuring security sustainable agriculture. By analyzing effect multiple on yield, presented research provides novel insights into potential impacts climate change production in India. In present study, datasets consisting countrywide agronomic were collected. addition, study also analyzes information farmers production. Methodology The employs regional analysis approach by dividing country five zonal clusters: Northern Hills, Central India, Indo-Gangetic Plains, North-Eastern Peninsular Correlation Principal Component Analysis (PCA) performed to uncover month-wise key affecting each zone. Furthermore, four Machine Learning/Deep Learning-based models, including XGBoost, Multi-layer Perceptron (MLP), Gated Recurrent Unit (GRU), 1-D Convolutional Neural Network (CNN), developed estimate yield. This estimated partial derivatives all using Newton's Quotient Technique, numerical method-based approach. Results focused applying this technique best-performing estimation model, which was GRU-based model (with RMSE MAE 0.60 t/ha 0.46 t/ha, respectively). Discussion later sections article, policy recommendations are communicated based extracted insights. results help inform decision-making regarding development strategies policies mitigate

Language: Английский

---

Applicability analysis of different evapotranspiration models for maize farmland in the lower Yellow River Plain based on eddy covariance measurements

Ecohydrology & Hydrobiology, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 1, 2024

Language: Английский

---

How to Measure Evapotranspiration in Landscape-Ecological Studies? Overview of Concepts and Methods

Journal of Landscape Ecology, Journal Year: 2024, Volume and Issue: 17(3), P. 38 - 59

Published: Nov. 23, 2024

Abstract Evapotranspiration (ET) is a key component of the hydrological cycle, encompassing evaporation processes from soil and water surfaces plant transpiration (Sun et al ., 2017). Accurate estimation ET vital for effective resource management, agricultural planning, environmental monitoring (Gowda 2008). However, complex interactions between land surface conditions, vegetation, atmospheric factors make direct measurement challenging, leading to development various methods. Remote sensing has become widely used approach estimating over large areas because it provides spatially comprehensive data (Xiao 2024). Methods like Surface Energy Balance Algorithm Land System utilise satellite-derived thermal imagery meteorological inputs calculate by analysing energy exchanges atmosphere. These methods are advantageous their broad spatial coverage, making them particularly useful regional global scale studies. they require careful calibration validation, accuracy can be affected resolution satellite quality inputs. In addition remote sensing, several other commonly employed. The Penman-Monteith equation one most accepted methods, integrating data—such as air temperature, humidity, wind speed, solar radiation— with biophysical properties vegetation estimate ET. This method been validated extensively, standard reference in Empirical Hargreaves-Samani provide simpler alternatives that fewer inputs, suitable regions limited information but trade-off accuracy. Direct techniques offer highly accurate data, including lysimeters eddy covariance systems. Lysimeters measure loss directly column, while systems assess exchange vapour Despite precision, these high costs, maintenance requirements, applicability small-scale, homogeneous (Howell, 2005). Choosing appropriate depends on study, availability, specific application. models scalability applicability, measurements precise at localised scales. Integrating improve reliability estimates, enhance aid climate adaptation efforts.

Language: Английский

---

Energy balance determination of crop evapotranspiration using a wireless sensor network

Frontiers in Agronomy, Journal Year: 2023, Volume and Issue: 5

Published: Oct. 16, 2023

Determining crop evapotranspiration (ET) is essential for managing water at various scales, from regional accounting to farm irrigation. Quantification of ET may be carried out by several procedures, being eddy covariance and energy balance the most established methods among research community. One major limitation high cost sensors included in or systems. We report here development a simpler device (CORDOVA-ET: COnductance Recording Device Observation VAlidation ET) determine based on industrial-grade, commercial off-the-shelf (COTS) costing far less than research-grade sensors. The CORDOVA-ET contains sensor package that integrates basic micrometeorological instrumentation infrared temperature required estimating over crops using approach. novel feature presence four different nodes allow determination locations within field fields same crop, thus allowing an assessment spatial variability. system was conceived as open-source hardware alternative devices, collaborative approach network countries North Africa Near East. Comparisons radiation, temperature, humidity, wind against those yielded excellent results, with coefficients correlation ( R 2 ) above 0.96. estimated reference calculated these measurements showed = 0.99 root mean square error (RMSE) 0.22 mm/day. RMSE below 0.56°C. components estimates were validated eddy-covariance wheat crop. net radiation (0.98), sensible heat (0.88), latent (0.86) good agreement between modeled fluxes measurements. components, acquisition, data processing software are available repositories facilitate adoption applications, use efficiency irrigation management.

Language: Английский

---

Predicting Tree Water Status in Pistachio and Almond Orchards Using Supervised Machine Learning

Published: Jan. 1, 2023

The advent of machine learning technologies in conjunction with the advancements UAV-based remote sensing pioneered a new era research agriculture. escalating concern for water management regions susceptible to drought such as California, underscores pressing need sustainable solutions. While stem potential (SWP) is considered most direct indicator tree status, labor-intensive nature SWP measurement using pressure chambers, necessitates more practical and efficient approach. To address this problem, we fused thermal (CWSI) multispectral (NDVI, GNDVI, OSAVI, LCI, NDRE) vegetation indices atmospheric parameters (T, P, RH) used (ML) algorithms classify almond pistachio trees. For each crop, deployed six supervised ML models: Random Forest (RF), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Tree (DT), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN). All classifiers provided than $\sim$80\% accuracy while (RF) led consistent performance at 88\% 89\% prediction pistachios almonds, respectively. feature importance results by RF model revealed that features were influential factors decision-making process. In both crops, CWSI was found be important index closely followed NDVI or optimized soil-adjusted (OSAVI).

Language: Английский

---

Artificial Neural Networks Estimate Evapotranspiration For Miscanthus × Giganteus As Effectively As Empirical Model But With Fewer Inputs

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: July 23, 2024

Estimating actual evapotranspiration (ET) is particularly crucial for addressing how vegetation affects the water balance of ecosystems. ET estimation can be complex with empirical models due to their many parameters and reliance on aridity. In contrast, artificial neural networks (ANNs) could potentially estimate fewer more common meteorological parameters. this study, we trained two ANNs, one using a feed-forward approach (FFN) other nonlinear auto-regressive network (NARX), predict compared them commonly used model Granger Gray (GG). We our nine-year eddy covariance (EC) dataset Miscanthus × giganteus (M. giganteus) from Illinois (UIEF), then tested out-of-sample data both UIEF different location in Iowa (SABR) compare accuracy FFN, NARX, GG estimating daily ET. A combination air temperature (T_a) solar radiation (R_s) was chosen as inputs highest R² FFN (R²= 0.79, 0.81, 0.79 training, testing, validation, respectively) only T_a NARX 0.70 validation). The predictive power superior at site 0.84, 0.70, 0.83 respectively). Our analysis showed that ANN approaches are accurate but use inputs.

Language: Английский

---

Generalization Ability of Bagging and Boosting Type Deep Learning Models in Evapotranspiration Estimation

Water, Journal Year: 2024, Volume and Issue: 16(16), P. 2233 - 2233

Published: Aug. 8, 2024

The potential of generalized deep learning models developed for crop water estimation was examined in the current study. This study conducted a semiarid region India, i.e., Karnataka, with daily climatic data (maximum and minimum air temperatures, maximum relative humidity, wind speed, sunshine hours, rainfall) 44 years (1976–2020) twelve locations. Extreme Gradient Boosting (XGBoost), (GB), Random Forest (RF) are three ensemble that were using all from single location (Bengaluru) January 1976 to December 2017 then immediately applied at eleven different locations (Ballari, Chikmaglur, Chitradurga, Devnagiri, Dharwad, Gadag, Haveri, Koppal, Mandya, Shivmoga, Tumkuru) without need any local calibration. For test period 2018–June 2020, model’s capacity estimate numerical values requirement (Penman-Monteith (P-M) ETo values) assessed. evaluated performance criteria mean absolute error (MAE), average (AARE), coefficient correlation (r), noise signal ratio (NS), Nash–Sutcliffe efficiency (ɳ), weighted standard (WSEE). results indicated WSEE RF, GB, XGBoost each smaller than 1 mm per day, effectiveness varied 96% 99% across various While performed better respect P-M approach, model able greater accuracy GB RF models. strong also by decreased noise-to-signal ratio. Thus, this study, mathematical short-term estimates is techniques. Because type calculating requirements its ability generalization, it can be effortlessly integrated real-time management system or an autonomous weather station regional level.

Language: Английский

---

Estimating actual crop evapotranspiration by using satellite images coupled with hybrid deep learning-based models in potato fields

Agricultural Water Management, Journal Year: 2024, Volume and Issue: 306, P. 109191 - 109191

Published: Dec. 1, 2024

Language: Английский

---