Search Results (40)

Insect pests remain a major threat to agricultural productivity, particularly in open-field cropping systems where conventional monitoring methods are labor-intensive and lack scalability. This study presents the design, implementation, and field evaluation of a neural network-guided smart trap specifically developed to monitor and selectively capture nocturnal insect pests under real agricultural conditions. The proposed trap integrates light and rain sensors, servo-controlled mechanical gates, and a single-layer perceptron neural network deployed on an ATmega-2560 microcontroller by Microchip Technology Inc. (Chandler, AZ, USA). The perceptron processes normalized sensor inputs to autonomously decide, in real time, whether to open or close the gate, thereby enhancing the selectivity of insect capture. The system features a removable tray containing a food-based attractant and yellow and green LEDs designed to lure target species such as moths and flies from the orders Lepidoptera and Diptera. Field trials were conducted between June and August 2023 in La Barca, Jalisco, Mexico, under diverse environmental conditions. Captured insects were analyzed and classified using the iNaturalist platform, with the successful identification of key pest species including Tetanolita floridiana, Synchlora spp., Estigmene acrea, Sphingomorpha chlorea, Gymnoscelis rufifasciata, and Musca domestica, while minimizing the capture of non-target organisms such as Carpophilus spp., Hexagenia limbata, and Chrysoperla spp. Statistical analysis using the Kruskal–Wallis test confirmed significant differences in capture rates across environmental conditions. The results highlight the potential of this low-cost device to improve pest monitoring accuracy, and lay the groundwork for the future integration of more advanced AI-based classification and species recognition systems targeting nocturnal Lepidoptera and other pest insects. Full article

This study investigates the linkage between the radar reflectivity slope and raindrop size distribution (DSD) in precipitation with bright bands through coordinated C-band/Ka-band radar and disdrometer observations in southern China. Precipitation is classified into three types based on the reflectivity slope (K-value) below the freezing level, revealing distinct microphysical regimes: Type 1 (K = 0 to −0.9) shows coalescence-dominated growth; Type 2 (|K| > 0.9) shows the balance between coalescence and evaporation/size sorting; and Type 3 (K = 0.9 to 0) demonstrates evaporation/size-sorting effects. Surface DSD analysis demonstrates distinct precipitation characteristics across classification types. Type 3 has the highest frequency of occurrence. A gradual decrease in the mean rain rates is observed from Type 1 to Type 3, with Type 3 exhibiting significantly lower rainfall intensities compared to Type 1. At equivalent rainfall rates, Type 2 exhibits unique microphysical signatures with larger mass-weighted mean diameters (D_m) compared to other types. These differences are due to Type 2 maintaining a high relative humidity above the freezing level (influencing initial D_m at bottom of melting layer) but experiencing limited D_m growth due to a dry warm rain layer and downdrafts. Type 1 shows opposite characteristics—a low initial D_m from the dry upper layers but maximum growth through the moist warm rain layer and updrafts. Type 3 features intermediate humidity throughout the column with updrafts and downdrafts coexisting in the warm rain layer, producing moderate growth. Full article

Accurate, real-time estimation of rainfall from Doppler radars remains a challenging problem, particularly over complex terrain where vertical beam sampling, atmospheric effects, and radar quality limitations introduce significant biases. In this work, we leverage citizen science rain gauge observations to develop a deep learning framework that corrects biases in radar-derived surface precipitation rates at high temporal resolution. A key step in our approach is the construction of piecewise-linear rainfall accumulation functions, which align gauge measurements with radar estimates and allow for the generation of high-quality instantaneous rain rate labels from rain gauge observations. After validating gauges through a two-stage temporal and spatial consistency filter, we train an adapted ResNet-101 model to classify rainfall intensity from sequences of surface precipitation rate estimates. Our model substantially improves precipitation classification accuracy relative to NOAA’s operational radar products within observed spatial regions, achieving large gains in precision, recall, and F1 score. While generalization to completely unseen regions remains more challenging, particularly for higher-intensity rainfall, modest improvements over baseline radar estimates are still observed in low-intensity rainfall. These results highlight how combining citizen science data with physically informed accumulation fitting and deep learning can meaningfully improve real-time radar-based rainfall estimation and support operational forecasting in complex environments. Full article

This study conducted a classification analysis of hydrometeor types during a typical stratiform mixed cloud precipitation event in the rainy season using data from the Liupan Mountains micro rain radar power spectra. The primary research findings are as follows: (1) Utilizing the RaProM method synthesizes the information of particle falling velocity, equivalent radar reflection coefficient, particle scale characteristics at different stages, and the location of the bright zone in the zero-degree layer to classify hydrometeors during this precipitation process, and the results show that drizzle and raindrop distribution time periods do not match with the raindrop spectra and rain intensities observed by the DSG5 ground-based precipitation gauge. (2) Sensitivity experiments conducted on the RaProM method revealed that after modifying the discrimination thresholds for drizzle and raindrops, the distributions of drizzle and raindrops were more aligned with ground-based raindrop spectrum observations. Furthermore, these adjustments also showed better consistency with the radar reflectivity factor, Doppler velocity, and velocity spectrum width thresholds used by existing millimeter-wave cloud radars to discriminate between drizzle and raindrops. (3) Various kinds of hydrometeors show different vertical distribution characteristics in three precipitation stages: weak, strong, and weak. In the two weak precipitation stages, hydrometeors mainly existed in the form of snowflakes at altitudes above the zero-degree layer and in the form of drizzle at altitudes below the zero-degree layer. The vertical distribution disparity of hydrometeors between the mountain peak and base sites demonstrates that terrain significantly influences hydrometeors during the precipitation process. Full article

Modeling the atmospheric boundary layer (ABL) in the area of a wind farm using computational fluid dynamics (CFD) methods allows us to study the characteristics of air movement, the shading effect, the influence of relief, etc., and can be actively used in studies of local territories where powerful wind farms are planned to be located. The operating modes of a wind farm largely depend on meteorological phenomena, the intensity and duration of which cause suboptimal operating modes of wind farms, which require the use of modern tools for forecasting and classifying precipitation. The methods and approaches used to predict meteorological phenomena are well known. However, for designed and operated wind farms, the influence of meteorological phenomena on the operating modes, such as freezing rain and hail, remains an urgent problem. This study presents a multi-layered neural network for the classification of precipitation zones, designed to identify adverse meteorological phenomena for wind farms according to weather stations. The neural network receives ten inputs and has direct signal propagation between six hidden layers. During the training of the neural network, an overall accuracy of 81.78%, macro-average memorization of 81.07%, and macro-average memorization of 75.05% were achieved. The neural network is part of an analytical module for making decisions on the application of control actions (control of the boundary layer of the atmosphere by injection of silver iodide, ionization, etc.) and the formation of the initial conditions for CFD modeling. Using the example of the Ulyanovsk wind farm, a study on the movement of air masses in the area of the wind farm was conducted using the initial conditions of the neural network. Digital models of wind turbines and terrain were created in the Simcenter STAR-CCM+ software package, version 2022.1; an approach based on a LES model using an actuating drive disk model (ADM) was implemented for modeling, allowing calculation with an error not exceeding 5%. According to the results of the modeling of the current layout of the wind turbines of the Ulyanovsk wind farm, a significant overlap of the turbulent wake of the wind turbines and an increase in the speed deficit in the area of the wind farm were noted, which significantly reduced its efficiency. A shortage of speed in the near and far tracks was determined for special cases of group placement of wind turbines. Full article

In recent years, the frequency and intensity of global extreme weather events have gradually increased, leading to significant changes in urban rainfall patterns. The uneven distribution of rainfall has caused varying degrees of water security issues in different regions. Accurately grasping the spatiotemporal distribution patterns of rainfall is crucial for understanding the hydrological cycle and predicting the availability of water resources. This study collected rainfall data every five minutes from 62 rain gauge stations in the main urban area of Kunming City from 2019 to 2021, constructing an unsupervised hybrid dimensionality reduction-clustering (HDRC) model. The model employs the Locally Linear Embedding (LLE) algorithm from manifold learning for dimensionality reduction of the data samples and uses the dynamic clustering K-Means algorithm for cluster analysis. The results show that the model categorizes the rainfall in the Kunming area into three types: The first type has its rainfall center distributed on the north shore of Dian Lake and the southern part of Kunming’s main urban area, with spatial dynamics showing the rainfall distribution gradually developing from the Dian Lake water body towards the land. The second type’s rainfall center is located in the northern mountainous area of Kunming, with a smaller spatial dynamic change trend. The water vapor has a relatively fixed and concentrated rainfall center due to the orographic uplift effect of the mountains. The third type’s rainfall center is located in the main urban area of Kunming, with this type of rainfall showing smaller variations in all indicators, mainly occurring in May and September when the temperature is lower, related to the urban heat island effect. This research provides a general workflow for spatial rainfall classification, capable of mining the spatiotemporal distribution patterns of regional rainfall based on extensive data and generating typical samples of rainfall types. Full article

Precipitation is the basic component of the Earth’s water cycle. Obtaining high-resolution and high-precision precipitation data is of great significance. This paper establishes a precipitation retrieval model based on a random forest classification and regression model during the day and at night with FY-4B/AGRI Level1 data on China from July to August 2022. To evaluate the retrieval effect of the model, the GPM IMERG product is used as a reference, and the retrieval results are compared against those of the FY-4B/AGRI operational precipitation product. In addition, the retrieval results are analyzed according to different underlying surfaces. The results showed that compared with the FY-4B/AGRI operational precipitation product, the retrieval model can better identify precipitation and capture precipitation areas of light rain, moderate rain, heavy rain and torrential rain. Among them, the probability of detection (POD) of the day model increased from 0.328 to 0.680, and the equitable threat score (ETS) increased from 0.252 to 0.432. The POD of the night model increased from 0.337 to 0.639, and the ETS score increased from 0.239 to 0.369. Meanwhile, the precipitation estimation accuracy of the day model increased by 38.98% and that of the night model increased by 40.85%. Our results also showed that due to the surface uniformity of the ocean, the model can identify precipitation better on the ocean than on the land. Our findings also indicated that for the different underlying surfaces of the land, there is no significant difference in each evaluation index of the model. This is a strong argument for the universal applicability of the model. Notably, the results showed that, especially for more vegetated areas and areas covered by water, the model is capable of estimating precipitation. In conclusion, the precipitation retrieval model that is proposed herein can better determine precipitation regions and estimate precipitation intensities compared with the FY-4B/AGRI operational precipitation product. It can provide some reference value for future precipitation retrieval research on FY-4B/AGRI. Full article

The China–France oceanography satellite scatterometer (CSCAT) is a rotating fan-beam scanning observation scatterometer operating in the Ku-band, and its product quality is affected by rain contamination. The multiple azimuthal NRCS measurements provided by CSCAT L2A, the retrieved wind speed and wind direction provided by CSCAT L2B, as well as the rain data provided by GPM, are used to construct a new rain identification and rain intensity classification model for CSCAT. The EXtreme Gradient Boosting (XGBoost) model, optimized by the Dung Beetle Optimizer (DBO) algorithm, is developed and evaluated. The performance of the DBO-XGBoost exceeds that of the CSCAT rain flag in terms of rain identification ability. Also, compared with XGBoost without parameter optimization, K-nearest Neighbor with K = 5 (KNN5) and K-nearest Neighbor with K = 3 (KNN3), the performance of DBO-XGBoost is better. Its rain identification achieves an accuracy of about 90% and a precision of about 80%, which enhances the quality control of rain. DBO-XGBoost has also shown good results in the classification of rain intensity. This ability is not available in traditional rain flags. In the global regional and local regional tests, most of the accuracy and precision in rain intensity classification have reached more than 80%. This technology makes full use of the rich observed information of CSCAT, realizes rain identification, and can also classify the rain intensity so as to further evaluate the degree of rain contamination of CSCAT products. Full article

Imaging disdrometers are widely used in field campaigns to provide information on the shape of hydrometeors, together with the diameter and the fall velocity, which can be used to derive information on the shape–size relations of hydrometeors. However, due to their higher price compared to laser disdrometers, their use is limited to scientific research purposes. The 3D stereo (3DS) is a commercial imaging disdrometer recently made available by Thies Clima and on which there are currently no scientific studies in the literature. The most innovative feature of the 3DS is its ability in capturing images of the particles passing through the measurement volume, crucial to provide an accurate classification of hydrometeors based on information about their shape, especially in the case of solid precipitation. In this paper. the performance of the new device is analyzed by comparing 3DS with the Laser Precipitation Monitor (LPM) from the same manufacturer, which is a known laser disdrometer used in many research works. The data used in this paper were obtained from measurements of the two instruments carried out at the Casale Calore site in L’Aquila during the CORE-LAQ (Combined Observations of Radar Experiments in L’Aquila) campaign. The objective of the comparison analysis is to analyze the differences between the two disdrometers in terms of hydrometeor classification, number and falling speed of particles, precipitation intensity, and total cumulative precipitation on an event basis. As regards the classification of precipitation, the two instruments are in excellent agreement in identifying rain and snow; greater differences are observed in the case of particles in mixed phase (rain and snow) or frozen phase (hail). Due to the different measurement area of the two disdrometers, the 3DS generally detects more particles than the LPM. The performance differences also depend on the size of the hydrometeors and are more significant in the case of small particles, i.e., D < 1 mm. In the case of rain events, the two instruments are in agreement with respect to the terminal velocity in still air predicted by the Gunn and Kinzer model for drops with a diameter of less than 3 mm, while, for larger particles, terminal velocity is underestimated by both the disdrometers. The agreement between the two instruments in terms of total cumulative precipitation per event is very good. Regarding the 3DS ability to capture images of hydrometeors, the raw data provide, each minute, from one to four images of single particles and information on their size and type. Their number and coarse resolution make them suitable to support only qualitative analysis of the shape of precipitating particles. Full article

Based on the high-resolution data from April to October (the warm season) during the 2010 to 2020 timeframe provided by the FY-2F geostationary meteorological satellite, the classification and application evaluation of the eastward-moving southwest vortex cloud system affecting Zhejiang Province was conducted using cloud classification (CLC) and black body temperature (TBB) products. The results show that: (1) when the intensity of the eastward-moving southwest vortex is strong, the formed precipitation is predominantly regional convective precipitation. The cloud system in the center and southeast quadrant of the southwest vortex is dominated by cumulonimbus and dense cirrus clouds with convective precipitation, while the other quadrants are mainly composed of stratiform clouds, resulting in stable precipitation; (2) The original text is modified as follows: By using the TBB threshold method to identify stratiform and mixed cloud rainfall, we observed a deviation of one order of magnitude. This deviation is advantageous for moderate rain. However, the precipitation results from mixed clouds identified by the TBB threshold method are being overestimated; By means of the application of stratiform and mixed cloud rainfall identified by the TBB threshold method, an order of magnitude deviation was identified (3) The TBB can be consulted to estimate the precipitation, above which there is a large error. Moreover, the dispersion of precipitation produced by deep convective clouds is the largest, while the dispersion of precipitation produced by stratiform clouds is the smallest and has better predictability. Compared to CLC products, cloud type results based on TBB identification are better for convective cloud precipitation application. Full article

Accurate and spatially distributed precipitation data are fundamental to effective water resource management. In Morocco, as in other arid and semi-arid regions, precipitation exhibits significant spatial and temporal variability. Indeed, there is an intra- and inter-annual variability and the northwest is rainier than the rest of the country. In the Bouregreg watershed, this irregularity, along with a sparse gauge network, poses a major challenge for water resource management. In this context, remote sensing data could provide a viable alternative. This study aims precisely to evaluate the performance of four gridded daily precipitation products: three IMERG-V06 datasets (GPM-F, GPM-L, and GPM-E) and a reanalysis product (ERA5). The evaluation is conducted using 11 rain gauge stations over a 20-year period (2000–2020) on various temporal scales (daily, monthly, seasonal, and annual) using a pixel-to-point approach, employing different classification and regression metrics of machine learning. According to the findings, the GPM products showed high accuracy with a low margin of error in terms of bias, RMSE, and MAE. However, it was observed that ERA5 outperformed the GPM products in identifying spatial precipitation patterns and demonstrated a stronger correlation. The evaluation results also showed that the gridded precipitation products performed better during the summer months for seasonal assessment, with relatively lower accuracy and higher biases during rainy months. Furthermore, these gridded products showed excellent performance in capturing different precipitation intensities, with the highest accuracy observed for light rain. This is particularly important for arid and semi-arid regions where most precipitation falls under the low-intensity category. Although gridded precipitation estimates provide global coverage at high spatiotemporal resolutions, their accuracy is currently insufficient and would require improvement. To address this, we employed an artificial neural network (ANN) model for bias correction and enhancing raw precipitation estimates from the GPM-F product. The results indicated a slight increase in the correlation coefficient and a significant reduction in biases, RMSE, and MAE. Consequently, this research currently supports the applicability of GPM-F data in North Western Morocco. Full article

Accurate and timely acquisition of cropping intensity and spatial distribution of paddy rice is not only an important basis for monitoring growth and predicting yields, but also for ensuring food security and optimizing the agricultural production management system of cropland. However, due to the monsoon climate in southern China, it is cloudy and rainy throughout the year, which makes it difficult to obtain accurate information on rice cultivation based on optical time series images. Conventional image synthesis is prone to omission or redundancy of spectral and temporal features that are potentially important for rice-growth identification, making it difficult to determine the optimal features for high-precision mapping of paddy rice. To address these issues, we develop a method to granulate the effective use interval of classification features by extracting phenological signatures of rice to obtain cost-effective and highly accurate mapping results. Two steps are involved in this method: (1) analyzing the information on various features (spectra, polarization, and seasonal regularity) to identify three key phenological periods throughout the lifespan of paddy rice; (2) identifying the features with the highest class separation between paddy rice, non-paddy crops, and wetlands under different phenological stages; and (3) removing redundant features to retain the optimal feature combinations. Subsequently, the obtained feature sets are used as input data for the random forest classifier. The results showed that the overall accuracy of the identified rice results was 95.44% with F1 scores above 93% for both single- and double-cropping rice. Meanwhile, the correlation coefficient of our mapped rice area compared with the official statistics of rice area at county and district levels was 0.86. In addition, we found that combining Sentinel-1 and Sentinel-2 images for rice recognition was better than using Sentinel-1 or Sentinel-2 alone, and the classification accuracy was improved by 5.82% and 2.39%, which confirms that the synergistic Sentinel-1 and Sentinel-2 data can effectively overcome the problem of missing optical images caused by clouds and rain. Our study demonstrates the potential of distinguishing mixed rice-cropping systems in subtropical regions with fragmented rice-field distribution in a cloudy and rainy environment, and also provides a basis for the rational layout of rice production and improvement of cultivation systems. Full article

This study evaluates the representativeness of two widely used next-generation global satellite precipitation estimates data for short-term precipitation over China, namely the satellite data from the Climate Prediction Center morphing (CMORPH) and the satellite data from the Global Precipitation Measurement (GPM) mission. These two satellite precipitation data sets were compared with the hourly liquid in-situ precipitation from China national surface stations from 2016 to 2020. The results showed that the GPM precipitation data has better representativeness of surface short-term precipitation than that of the CMORPH data, and these two quantitative precipitation estimate (QPE) data sets underestimated extreme precipitation. Moreover, we analyzed the influence of the error between two QPE data sets and the in-situ precipitation on the classification of short-term precipitation intensity. China uses 8.1–16 mm/h as the definition of heavy precipitation, but the accuracy of the satellite QPE product was different due to the different lowest threshold of heavy rain (more than 8.1 mm/h or more than 16 mm/h). Increasing the threshold value of the QPE data for short-term strong precipitation resulted in lower accuracy for detecting such events, but higher accuracy for detecting moderate intensity rainfall. When studying short-term strong precipitation over China using precipitation grade, selecting an appropriate threshold was important to ensure accurate judgments. Additionally, it is important to account for errors caused by QPE data, which can significantly affect the accuracy of precipitation grading. Full article

Every farmer requires access to rainfall prediction (RP) to continue their exploration of harvest yield. The proper use of water assets, the successful collection of water, and the successful pre-growth of water construction all depend on an accurate assessment of rainfall. The prediction of heavy rain and the provision of information regarding natural catastrophes are two of the most challenging factors in this regard. In the twentieth century, RP was the most methodically and technically complicated issue worldwide. Weather prediction may be used to calculate and analyse the behaviour of weather with unique features and to determine rainfall patterns at an exact locale. To this end, a variety of methodologies have been used to determine the rainfall intensity in Saudi Arabia. The classification methods of data mining (DM) approaches that estimate rainfall both numerically and categorically can be used to achieve RP. This study, which used DM approaches, achieved greater accuracy in RP than conventional statistical methods. This study was conducted to test the efficacy of several machine learning (ML) approaches for forecasting rainfall, utilising southern Saudi Arabia’s historical weather data obtained from the live database that comprises various meteorological data variables. Accurate crop yield predictions are crucial and would undoubtedly assist farmers. While engineers have developed analysis systems whose performance relies on several connected factors, these methods are seldom used despite their potential for precise crop yield forecasts. For this reason, agricultural forecasting should make use of these methods. The impact of drought on crop yield can be difficult to forecast and there is a need for careful preparation regarding crop choice, planting window, harvest motive, and storage space. In this study, the relevant characteristics required to predict precipitation were identified and the ML approach utilised is an innovative classification method that can be used determine whether the predicted rainfall will be regular or heavy. The outcomes of several different methodologies, including accuracy, error, recall, F-measure, RMSE, and MAE, are used to evaluate the performance metrics. Based on this evaluation, it is determined that DT provides the highest level of accuracy. The accuracy of the Function Fitting Artificial Neural Network classifier (FFANN) is 96.1%, which is higher than that of any of the other classifiers currently used in the rainfall database. Full article

In the climate change scenario the world is facing, extreme weather events can lead to increasingly serious disasters. To improve managing the consequent risks, there is a pressing need to have real-time systems that provide accurate monitoring and possibly forecasting which could help to warn people in the affected areas ahead of time and save them from hazards. The oblique earth-space links (OELs) have been used recently as a method for real-time rainfall detection. This technique poses two main issues related to its indirect nature. The first one is the classification of rainy and non-rainy periods. The second one is the determination of the attenuation baseline, which is an essential reference for estimating rainfall intensity along the link. This work focuses mainly on the first issue. Data referring to eighteen rain events were used and have been collected by analyzing a satellite-to-earth link quality and employing a tipping bucket rain gauge (TBRG) properly positioned, used as reference. It reports a comparison among the results obtained by applying four different machine learning (ML) classifiers, namely the support vector machine (SVM), neural network (NN), random forest (RF), and decision tree (DT). Various data arrangements were explored, using a preprocessed version of the TBRG data, and extracting two different sets of characteristics from the microwave link data, containing 6 or 12 different features, respectively. The achieved results demonstrate that the NN classifier has outperformed the other classifiers. Full article