This study investigated the drivers of degradation in Southeast Asian mangroves through multi-source remote sensing data products. The degradation drivers that affect approximately half of this area are unidentified; therefore, naturogenic and anthropogenic impacts on these mangroves were studied. Various global land cover (GLC) products were harmonized and examined to identify major anthropogenic changes affecting mangrove habitats. To investigate the naturogenic factors, the impact of the water balance was evaluated using the Normalized Difference Vegetation Index (NDVI), and evapotranspiration and precipitation data. Vegetation indices’ response in deforested mangrove regions depends significantly on the type of drivers. A trend analysis and break point detection of percentage of tree cover (PTC), percentage of non-tree vegetation (PNTV), and percentage of non-vegetation (PNV) datasets can aid in measuring, estimating, and tracing the drivers of change. The assimilation of GLC products suggests that agriculture and fisheries are the predominant drivers of mangrove degradation. The relationship between water balance and degradation shows that naturogenic drivers have a wider impact than anthropogenic drivers, and degradation in particular regions is likely to be a result of the accumulation of various drivers. In large-scale studies, remote sensing data products could be integrated as a remarkably powerful instrument in assisting evidence-based policy making.

High-resolution images captured by Unmanned Aerial Vehicles (UAVs) play a vital role in precision agriculture, particularly in evaluating crop health and detecting weeds. However, the detailed pixel information in these images makes classification a time-consuming and resource-intensive process. Despite these challenges, UAV imagery is increasingly utilized for various agricultural classification tasks. This study introduces an automatic classification method designed to streamline the process, specifically targeting cassava plants, weeds, and soil classification. The approach combines K-means unsupervised classification with spectral trend-based labeling, significantly reducing the need for manual intervention. The method ensures reliable and accurate classification results by leveraging color indices derived from RGB data and applying mean-shift filtering parameters. Key findings reveal that the combination of the blue (B) channel, Visible Atmospherically Resistant Index (VARI), and color index (CI) with filtering parameters, including a spatial radius (sp) = 5 and a color radius (sr) = 10, effectively differentiates soil from vegetation. Notably, using the green (G) channel, excess red (ExR), and excess green (ExG) with filtering parameters (sp = 10, sr = 20) successfully distinguishes cassava from weeds. The classification maps generated by this method achieved high kappa coefficients of 0.96, with accuracy levels comparable to supervised methods like Random Forest classification. This technique offers significant reductions in processing time compared to traditional methods and does not require training data, making it adaptable to different cassava fields captured by various UAV-mounted optical sensors. Ultimately, the proposed classification process minimizes manual intervention by incorporating efficient pre-processing steps into the classification workflow, making it a valuable tool for precision agriculture.

Droughts impose severe global challenges by affecting water resources, agricultural productivity, and ecosystems, and presenting considerable socioeconomic risks. In the Western United States, increasing aridity and reliance on limited water sources aggravate these issues. Accurate and timely drought forecasting is essential for effective water management, mitigating agricultural impacts, and addressing broader economic and environmental concerns. This research introduces a novel approach for early drought prediction by using remotely sensed data, with a specific focus on the drought-prone states of California and Nevada. We analyse MODIS (Moderate Resolution Imaging Spectroradiometer) time series data from 2001 to 2015 to derive indices such as the Vegetation Condition Index (VCI) and Temperature Condition Index (TCI), These indices serve as monthly indicators of drought severe. We utilize the Long Short-Term Memory (LSTM) model to predict the Vegetation Condition Index (VCI), Temperature Condition Index (TCI). Subsequently, the annual average values of these indices are employed with linear regression to estimate drought severity levels. The results indicate that this hybrid approach enhances predictive accuracy by effectively integrating temporal dynamics with vegetation indices, providing actionable drought forecasts.

Using the high-resolution image from UAV is a major challenge for crop classification. The lighting conditions play an essential role in altering spectral reflectance, affecting the classification accuracy. With this barrier, it is difficult to use a single training data set in machine learning and apply to the images taken on different dates and times. This study aims to demonstrate the application of vegetation indices combined with the red, green, or blue dataset to enhance the image classification by using the Unsupervised classification method with the K-mean technic. This study shows the experiments of using three same image layers in three different windows of mean shift filter and presents the experiments of using three different image layers in three different windows. The optimal dataset shows Thailand's best performance of eight traditional cassava fields. As a result, three of the same BI and Blue layers presented the optimal dataset, Kappa coefficient = 0.864938 and 0.729271 for soil and plant classification, respectively. Alternatively, using a different dataset as the input to three windows of the mean shift filters was considered in this study to compare the results with the single-type input. The criterion of one primary dataset and two indices showed the optimal dataset among those experimental results (Kappa coefficient > 0.948681) in soil classification, as well as the optimal dataset for plant classification (Kappa coefficient > 0.773652). It can be concluded that combining complementary spectral features captured by different indices makes the classification model more robust and capable of capturing a broader range of soil characteristics, resulting in higher accuracy and reliability in delineating soil boundaries and plants in the cassava fields.

Background/Objectives: Ultrasound is widely used for breast cancer screening and diagnosis, particularly in low- and middle-income settings, but its diagnostic reliability is often compromised by speckle noise that degrades lesion margins and tissue texture. This study proposes a compact convolutional neural network architecture that replaces standard max or average pooling layers with wavelet-based pooling using Symlet families, and optionally includes wavelet-domain preprocessing to suppress input noise. Methods: We conducted 108 experiments across six pooling configurations (avg, max, Sym2 ± preprocessing, Sym4 + preprocessing, Sym6 + preprocessing), two network depths, three batch sizes, and three simulated speckle levels (0%, 10%, 20%). Results: The proposed wavelet-based pooling framework showed consistently stronger in-domain performance than conventional pooling strategies across clean and speckle-corrupted settings, with the Sym2 + preprocessing configuration giving the best overall results. The model achieved 93.90% accuracy and 98.89% ROC AUC under clean internal test conditions and maintained stable performance under increased simulated noise levels. However, external validation on the independent BrEaST-Lesions-USG dataset revealed substantial performance degradation, with accuracy decreasing to 53.97% and ROC AUC to 0.4713, indicating limited cross-dataset generalization. Conclusions: These findings suggest that wavelet pooling is an effective architectural modification for improving in-domain robustness under controlled perturbation, although additional strategies are still required before reliable real-world deployment can be claimed.

Satellite-based rainfall datasets such as CHIRPS and GPM provide valuable information for hydrological and agricultural studies but often contain systematic biases when compared with ground measurements. The accurate estimation of rainfall is also critical for disaster management, particularly in mitigating the impacts of both floods and droughts. This study applies three bias correction techniques Variance Scaling (VS), Quantile Mapping (QM), and Linear Regression (LR), to rainfall data from 37 ground stations in Nakhon Ratchasima Province, Thailand, covering the period 2002–2022, a region that regularly faces significant drought problems. Comparative analyses show that raw satellite products generally overestimate rainfall relative to gauge observations. Among the correction methods, VS consistently delivered the best performance by reducing bias and RMSE while improving correlation across stations. QM achieved mixed results and sometimes increased error, particularly for GPM. LR, while less effective than VS in bias reduction, provided stable correlations and thus offers potential as a baseline for future rainfall forecasting models. These findings underscore the importance of bias correction for enhancing the reliability of satellite rainfall datasets in complex tropical terrains.