Exploring Machine Learning Models for Soil Nutrient Properties Prediction: A Systematic Review

Big Data and Cognitive Computing, Journal Year: 2023, Volume and Issue: 7(2), P. 113 - 113

Published: June 8, 2023

Agriculture is essential to a flourishing economy. Although soil for sustainable food production, its quality can decline as cultivation becomes more intensive and demand increases. The importance of healthy cannot be overstated, lack nutrients significantly lower crop yield. Smart prediction digital mapping offer accurate data on nutrient distribution needed precision agriculture. Machine learning techniques are now driving intelligent systems. This article provides comprehensive analysis the use machine in predicting qualities. components qualities soil, parameters, existing dataset, map, effect growth, well information system, key subjects under inquiry. agriculture, exemplified by this study, improve productivity.

Language: Английский

---

Estimating soil moisture content in citrus orchards using multi-temporal sentinel-1A data-based LSTM and PSO-LSTM models

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 637, P. 131336 - 131336

Published: May 12, 2024

Language: Английский

---

Improving soil moisture prediction with deep learning and machine learning models

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 226, P. 109414 - 109414

Published: Sept. 14, 2024

Language: Английский

---

Unleashing the power of machine learning and remote sensing for robust seasonal drought monitoring: A stacking ensemble approach

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 634, P. 131102 - 131102

Published: March 22, 2024

Language: Английский

---

Estimation of winter canola growth parameter from UAV multi-angular spectral-texture information using stacking-based ensemble learning model

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 222, P. 109074 - 109074

Published: May 23, 2024

Language: Английский

---

Integration of Remote Sensing and Machine Learning for Precision Agriculture: A Comprehensive Perspective on Applications

Agronomy, Journal Year: 2024, Volume and Issue: 14(9), P. 1975 - 1975

Published: Sept. 1, 2024

Due to current global population growth, resource shortages, and climate change, traditional agricultural models face major challenges. Precision agriculture (PA), as a way realize the accurate management decision support of production processes using modern information technology, is becoming an effective method solving these In particular, combination remote sensing technology machine learning algorithms brings new possibilities for PA. However, there are relatively few comprehensive systematic reviews on integrated application two technologies. For this reason, study conducts literature search Web Science, Scopus, Google Scholar, PubMed databases analyzes in PA over last 10 years. The found that: (1) because their varied characteristics, different types data exhibit significant differences meeting needs PA, which hyperspectral most widely used method, accounting more than 30% results. UAV offers greatest potential, about 24% data, showing upward trend. (2) Machine displays obvious advantages promoting development vector algorithm 20%, followed by random forest algorithm, 18% methods used. addition, also discusses main challenges faced currently, such difficult problems regarding acquisition processing high-quality model interpretation, generalization ability, considers future trends, intelligence automation, strengthening international cooperation sharing, sustainable transformation achievements. summary, can provide ideas references combined with promote

Language: Английский

---

Random Forest-Based Soil Moisture Estimation Using Sentinel-2, Landsat-8/9, and UAV-Based Hyperspectral Data

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(11), P. 1962 - 1962

Published: May 29, 2024

Accurate spatiotemporal monitoring and modeling of soil moisture (SM) is paramount importance for various applications ranging from food production to climate change adaptation. This study deals with SM the random forest (RF) algorithm using datasets comprising multispectral data Sentinel-2, Landsat-8/9, hyperspectral CoSpectroCam sensor (CSC, licensed AgriWatch BV, Enschede, The Netherlands) mounted on an unmanned aerial vehicle (UAV) in Iran. model included nine bands 11 1252 CSC (covering wavelength range between 420 850 nm). relative feature band sensitivity variations were analyzed. In addition, four indices, including perpendicular index (PI), ratio (RI), difference (DI), normalized (NDI) calculated different datasets, their was evaluated. results showed that PI exhibited highest changes all among indices considered. Comparisons performance estimation emphasized superior UAV (R2 = 0.87), while Sentinel-2 Landsat-8/9 lower accuracy 0.49 0.66, respectively). robust likely due its spatial spectral resolution as well application preprocessing techniques such noise reduction smoothing filters. can also be attributed relatively coarse compared CSC, which leads pixel non-uniformities impurities. Therefore, employing a proves valuable technology, providing effective link satellite observations ground measurements.

Language: Английский

---

Development and Comparison of Artificial Neural Networks and Gradient Boosting Regressors for Predicting Topsoil Moisture Using Forecast Data

AI, Journal Year: 2025, Volume and Issue: 6(2), P. 41 - 41

Published: Feb. 19, 2025

Introduction: The Earth’s growing population is increasing resource consumption, heavily pressuring agriculture, which, currently, uses 70% of the world’s freshwater from rivers and lakes, themselves, comprise only 1% water reserves. Combined with climate change, situation alarming. These challenges drive Agriculture 4.0, which focused on sustainable agricultural processes to optimise use. Objective: Given this context, study proposes a model, based Artificial Intelligence (AI) techniques predict topsoil moisture in area located south Iberian Peninsula, primarily an region facing recurrent droughts scarcity. Methods: To develop comparison between Neural Networks (ANNs) Gradient Booster Regressors (GBRs) was conducted, data seven probes distributed over were used, addition several variables (temperature, relative humidity, solar radiation, wind speed, precipitation evapotranspiration) selection weather stations ensemble forecasts meteorological models. Results: final GBR 0.01 learning rate, 5 max depth, 350 estimators, predicted average mean squared error (MSE) 0.027 maximum difference observed 20.09% two-year series (May 2022–June 2024).

Language: Английский

---

Application of machine learning algorithms to model soil thermal diffusivity

International Communications in Heat and Mass Transfer, Journal Year: 2023, Volume and Issue: 149, P. 107092 - 107092

Published: Oct. 17, 2023

Language: Английский

---

Modelling soil moisture using climate data and normalized difference vegetation index based on nine algorithms in alpine grasslands

Frontiers in Environmental Science, Journal Year: 2023, Volume and Issue: 11

Published: Feb. 10, 2023

Soil moisture (SM) is closely correlated with ecosystem structure and function. Examining whether climate data (temperature, precipitation radiation) the normalized difference vegetation index (NDVI) can be used to estimate SM variation could benefit research related under change human activities. In this study, we evaluated ability of nine algorithms explain potential (SM p ) using actual a NDVI. Overall, NDVI based on constructed random forest models led best estimated ( R 2 ≥ 94%, RMSE ≤ 2.98, absolute value relative bias: 3.45%). Randomness, setting values two key parameters mtry ntree ), may why obtained highest accuracy in predicating SM. Therefore, study thus applied spatiotemporal variations for other scientific (e.g., differentiating effects activities SM), at least Tibetan grassland region.

Language: Английский

---