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

---

Precipitation nowcasting using transformer-based generative models and transfer learning for improved disaster preparedness

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 132, P. 103962 - 103962

Published: July 1, 2024

Due to the rapidly changing climate conditions, precipitation nowcasting poses a daunting challenge because it is impossible make accurate short-term forecasts due rapid fluctuations in weather conditions. There are limitations traditional methods of forecasting precipitation, such as use numerical models and radar extrapolation, when comes providing highly detailed timely forecasts. With help contemporary machine learning (ML) models, including deep neural networks, transformers generative complex tasks can be performed an efficient way. To address this critical task enhance proactive emergency disaster management, we propose innovative method based on transformer-based for nowcasting. Our study area Soyang Dam basin South Korea, located upstream Han River, characterized by monsoon with approximately 1200 mm annual precipitation. develop model, composite data from 10 radars across Korea used. By utilizing reflective order train our able effectively predict future patterns, thus mitigating risk catastrophic conditions caused heavy rainfalls. This dataset covers reflectivity 2018 2022, spatial resolution 1km over 960 × grid. Normalization using min–max scaler applied data, which then transformed into grayscale images uniform comparison. We performance employing transfer pre-trained Transformer models. Initially, model comprehensive dataset. Subsequently, fine-tune data. adaptation improves accuracy rainfall capturing crucial features. Leveraging prior knowledge through not only enhances prediction but also increases overall efficiency. In terms predictive accuracy, extensive experimental results demonstrate that outperforms related approaches, conditional adversarial networks (cGANs), U-Net, convolutional long memory (ConvLSTM), pySTEP. As result research, preparedness response will greatly improved prediction.

Language: Английский

---

Estimating Leaf Chlorophyll Content of Winter Wheat from UAV Multispectral Images Using Machine Learning Algorithms under Different Species, Growth Stages, and Nitrogen Stress Conditions

Agriculture, Journal Year: 2024, Volume and Issue: 14(7), P. 1064 - 1064

Published: July 1, 2024

The rapid and accurate estimation of leaf chlorophyll content (LCC), an important indicator crop photosynthetic capacity nutritional status, is great significance for precise nitrogen fertilization management. To explore the existence a versatile regression model that can be successfully used to estimate LCC different varieties under growth stages stress conditions, study was conducted in 2023 across growing season winter wheat with five species application levels. Two machine learning algorithms, support vector (SVM) random forest (RF), were establish bridge between UAV-derived multispectral vegetation indices ground truth (relative content, SPAD), taking multivariate linear (MLR) algorithm as reference. results show visible atmospherically resistant index, vegetative normalized difference index had highest correlation LCC, Pearson’s coefficient 0.95. All three algorithms (MLR, RF, SVM) performed well on training dataset (R2: 0.932–0.944, RMSE: 3.96 4.37), but differently validation datasets stages, species, Compared levels, greatest influence generalization ability models, especially dough stage. At stage, compared MLR SVM best, R2 increasing by 0.27 0.10, respectively, RMSE decreasing 1.13 0.46, respectively. Overall, this demonstrated combination VIs could applied map conditions. Ultimately, research significant it shows successful UAV data mapping diverse offering valuable insights precision

Language: Английский

---

Random forest machine learning for maize yield and agronomic efficiency prediction in Ghana

Heliyon, Journal Year: 2024, Volume and Issue: 10(17), P. e37065 - e37065

Published: Aug. 28, 2024

Highlights•Random forest modelling of maize yield in Ghana was successful and explained 81 % the variance.•Random agronomic efficiency less accurate than for between 53 63 variance.•Soil variables were more important climate other environmental predicting yield.•The random model can guide development fertilizer recommendations sustainable production.AbstractMaize (Zea mays) is an staple crop food security Sub-Saharan Africa. However, there need to increase production feed a growing population. In Ghana, this mainly done by increasing acreage with adverse consequences, rather increment per unit area. Accurate prediction yields nutrient use critical making informed decisions toward economic ecological sustainability. We trained machine learning algorithm predict using soil, climate, environment, management factors, including application. calibrated evaluated performance 5 × 10-fold nested cross-validation approach. Data from 482 field trials consisting 3136 georeferenced treatment plots conducted 1991 2020 used train algorithm, identify predictor variables, quantify uncertainties associated predictions. The mean error, root squared coefficient 90 interval coverage probability calculated. results obtained on test data demonstrate good (MEC = 0.81) moderate 0.63, 0.55 0.54 AE-N, AE-P AE-K, respectively). found that climatic predictors soil prediction, but temperature key importance rainfall efficiency. developed models provided better understanding drivers tropical insight towards improving

Language: Английский

---

Evaluation of Machine Learning Regression Techniques for Estimating Winter Wheat Biomass Using Biophysical, Biochemical, and UAV Multispectral Data

Drones, Journal Year: 2024, Volume and Issue: 8(7), P. 287 - 287

Published: June 26, 2024

Crop above-ground biomass (AGB) estimation is a critical practice in precision agriculture (PA) and vital for monitoring crop health predicting yields. Accurate AGB allows farmers to take timely actions maximize yields within given growth season. The objective of this study use unmanned aerial vehicle (UAV) multispectral imagery, along with derived vegetation indices (VI), plant height, leaf area index (LAI), nutrient content ratios, predict the dry (g/m2) winter wheat field southwestern Ontario, Canada. This assessed effectiveness Random Forest (RF) Support Vector Regression (SVR) models ABG from 42 variables. RF consistently outperformed SVR models, top-performing model utilizing 20 selected variables based on their contribution increasing node purity decision trees. achieved an R2 0.81 root mean square error (RMSE) 149.95 g/m2. Notably, included combination MicaSense bands, VIs, levels, height. significantly all other that relied solely UAV data or content. insights gained can enhance management AGB, leading more effective yield predictions management.

Language: Английский

---

Unmanned Aerial Vehicle-Measured Multispectral Vegetation Indices for Predicting LAI, SPAD Chlorophyll, and Yield of Maize

Agriculture, Journal Year: 2024, Volume and Issue: 14(7), P. 1110 - 1110

Published: July 9, 2024

Predicting crop yield at preharvest is pivotal for agricultural policy and strategic decision making. Despite global targets, labour-intensive surveys estimation pose challenges. Using unmanned aerial vehicle (UAV)-based multispectral sensors, this study assessed phenology biotic stress conditions using various spectral vegetation indices. The goal was to enhance the accuracy of predicting key parameters, such as leaf area index (LAI), soil plant analyser development (SPAD) chlorophyll, grain maize. study’s findings demonstrate that during kharif season, wide dynamic range (WDRVI) showcased superior correlation coefficients (R), determination (R2), lowest root mean square errors (RMSEs) 0.92, 0.86, 0.14, respectively. However, rabi atmospherically resistant (ARVI) achieved highest R R2 RMSEs 0.83, 0.79, 0.15, respectively, indicating better in LAI. Conversely, normalised difference red-edge (NDRE) season modified chlorophyll absorption ratio (MCARI) were identified predictors with SPAD prediction. Specifically, values 0.91 0.94, 0.83 0.82, RMSE 2.07 3.10 obtained, most effective indices LAI prediction (WDRVI NDRE) (ARVI MCARI) further utilised construct a model stepwise regression analysis. Integrating predicted into resulted higher compared individual predictions. More exactly, 0.51 0.74, while 9.25 6.72, seasons, These underscore utility UAV-based imaging yields, thereby aiding sustainable management practices benefiting farmers policymakers alike.

Language: Английский

---

Ground-Based Hyperspectral Estimation of Maize Leaf Chlorophyll Content Considering Phenological Characteristics

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(12), P. 2133 - 2133

Published: June 13, 2024

Accurately measuring leaf chlorophyll content (LCC) is crucial for monitoring maize growth. This study aims to rapidly and non-destructively estimate the LCC during four critical growth stages investigate ability of phenological parameters (PPs) LCC. First, spectra were obtained by spectral denoising followed transformation. Next, sensitive bands (Rλ), indices (SIs), PPs extracted from all at each stage. Then, univariate models constructed determine their potential independent estimation. The multivariate regression (LCC-MR) built based on SIs, SIs + Rλ, Rλ after feature variable selection. results indicate that our machine-learning-based LCC-MR demonstrated high overall accuracy. Notably, 83.33% 58.33% these showed improved accuracy when successively introduced SIs. Additionally, model accuracies milk-ripe tasseling outperformed those flare–opening jointing under identical conditions. optimal was created using XGBoost, incorporating SI, PP variables R3 These findings will provide guidance support management.

Language: Английский

---

Surface displacement measurement and modeling of the Shah-Gheyb salt dome in southern Iran using InSAR and machine learning techniques

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 132, P. 104016 - 104016

Published: July 11, 2024

Salt domes play a crucial role in hydrocarbon storage, underground construction, solution mining, and mineralization. Therefore, deformation monitoring is essential for analyzing the kinematics impact of salt domes. This study aims to measure temporal displacements Shah-Gheyb dome from 2016 2019 2020 2022 using New Small Baseline Subset (NSBAS) Interferometric Synthetic Aperture Radar (InSAR) technique predict future through machine learning models. A total 14 data layers, including topography, remote sensing, hydrology, geology group were used Machine Learning (ML). Random Forest Regression (RFR) Support Vector (SVR) models employed project both East-West (E-W) Up-Down (U-D) components 29 scenarios. In E-W direction, exhibits displacement rate 39 mm/year, while U-D it varies between −18 +6 mm/year. ML predictions SAR interferometry processing results period 2020–2022 validated Root Mean Square Error (RMSE) correlation coefficient (R). The RFR model demonstrated lowest RMSE 1.9 mm component, achieving maximum R-value 97.3 %. For was 2.8 mm, with an 55.8 Evaluation predictive performance comparison InSAR outcomes indicated that predicted along directions greater accuracy than SVR. Furthermore, comparing by two perpendicular profiles confirmed model's precision.

Language: Английский

---

Synergistic approach for land use and land cover dynamics prediction in Uttarakhand using cellular automata and Artificial neural network

GEOMATICA, Journal Year: 2024, Volume and Issue: 76(2), P. 100017 - 100017

Published: Aug. 10, 2024

Alterations in Land use and cover (LULC) stand out as a key catalyst for shifts global climate patterns, environmental conditions, ecological dynamics. In order to further enhance our comprehension of the effects variability on environment, Remote sensing GIS analytical approaches have been thoroughly explored are reflected an imperative vision. Thus, objective this study is model Uttarakhand's LULC pattern 2032 analyse changes trend between 1992 2022. change mapping was conducted utilizing semi-automated hybrid classification approach high level accuracy which integrates both Maximum likelihood Object based image analysis techniques Landsat datasets. The machine learning Cellular automata Artificial neural networks (CA-ANN) within MOLUSCE plugin QGIS applied future patterns. assessment results showed that overall years 1992, 2002, 2012, 2022 96.94 %, 97.77 98.61 % 98.87 respectively, kappa statistics coefficient 0.92, 0.95, 0.94 0.95 respectively. simulated projected map implies substantially accuracy, with Kappa value 0.77 85.39 correctness. Then, year predicted using CA-ANN. observed alterations significant, characterized by augmentation built-up areas, open land, water bodies, alongside decline snow-covered regions, vegetation cover. Whereas, slight increase seen Forested areas. Planners policy makers aiming accomplish more sustainable efficient management environment will find over prolonged period time be useful asset optimal land planning.

Language: Английский

---

Grain Crop Yield Prediction Using Machine Learning Based on UAV Remote Sensing: A Systematic Literature Review

Drones, Journal Year: 2024, Volume and Issue: 8(10), P. 559 - 559

Published: Oct. 8, 2024

Preharvest crop yield estimation is crucial for achieving food security and managing growth. Unmanned aerial vehicles (UAVs) can quickly accurately acquire field growth data are important mediums collecting agricultural remote sensing data. With the rapid development of machine learning, especially deep research on based UAV learning has achieved excellent results. This paper systematically reviews current through a search 76 articles, covering aspects such as grain crops studied, questions, collection, feature selection, optimal models, periods estimation. Through visual narrative analysis, conclusion covers all proposed questions. Wheat, corn, rice, soybeans main objects, mechanisms nitrogen fertilizer application, irrigation, variety diversity, gene diversity have received widespread attention. In modeling process, selection key to improving robustness accuracy model. Whether single modal features or multimodal research, multispectral images source information. The model may vary depending selected period but random forest convolutional neural networks still perform best in most cases. Finally, this study delves into challenges currently faced terms volume, optimization, determining period, algorithm limitations UAVs. Further needed areas augmentation, engineering, improvement, real-time future.

Language: Английский

---