Forest Classifier Research Articles

Quantifying effects of changes in forest age distribution on the landslide frequency in Japan

Landslides are destructive natural disasters that cause human and economic losses. Although many studies report the effects of forest age on landslide susceptibility, especially for shallow landslides, no studies have examined the effects at a national scale. We assumed that temporal variations in the annual number of rainfall-triggered landslides in Japan were determined by variations in rainfall and forest age distribution. By this assumption, this study aimed to quantify the decrease in the frequency of rainfall-induced landslides owing to the increasing maturity of forests in Japan. Data were collated from 21 studies covering 11 sites in three countries that reported a landslide susceptibility index (i.e., frequency ratio or landslide density) and the relation between forest age and the normalized landslide susceptibility index (NLSI) was modeled. Using this relation and the area for each forest age class, the change in landslide susceptibility at a national scale (NLSIJpn) was quantified during 1966–2017. The authors developed generalized linear models (GLMs) using the annual number of landslides as the response variable and the NLSIJpn and a rainfall index for each year as the explanatory variables. The number of rainfall-induced landslides was simulated in the GLMs in 15 scenarios with different forest age distributions and rainfall amounts. The number of landslides in young-age-dominated and middle-age-dominated forests was estimated to be 2.4 and 1.1 times, respectively, that in mature-age-dominated forests. The change in the number of landslides from young-age-dominated to mature-age-dominated forests was larger than that from an increase in the rainfall amount of 20%. We conclude that increasing the maturity of forests greatly reduces landslide frequency in Japan. In a changing climate with potentially threatening increases in rainfall, preserving mature forests is important to avoid amplifying landslide susceptibility on a national scale.

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields.

This study aimed to develop and validate algorithms for automating intensity modulated radiation therapy (IMRT) planning in breast cancer patients, with a focus on patient anatomical characteristics. We retrospectively selected 400 breast cancer patients without lymph node involvement for automated treatment planning. Automation was achieved using the Eclipse Scripting Application Programming Interface (ESAPI) integrated into the Eclipse Treatment Planning System. We employed three beam insertion geometries and three optimization strategies, resulting in 3600 plans, each delivering a 40.05Gy dose in 15 fractions. Gantry angles in the tangent fields were selected based on a criterion involving the minimum intersection area between the Planning Target Volume (PTV) and the ipsilateral lung in the Beam's Eye View projection. ESAPI was also used to gather patient anatomical data, serving as input for Random Forest models to select the optimal plan. The Random Forest classification considered both beam insertion geometry and optimization strategy. Dosimetric data were evaluated in accordance with the Radiation Therapy Oncology Group (RTOG) 1005 protocol. Overall, all approaches generated high-quality plans, with approximately 94% meeting the acceptable dose criteria for organs at risk and/or target coverage as defined by RTOG guidelines. Average automated plan generation time ranged from 6 min and 37 s to 9 min and 22 s, with the mean time increasing with additional fields. The Random Forest approach did not successfully enable automatic planning strategy selection. Instead, our automated planning system allows users to choose from the tested geometry and strategy options. Although our attempt to correlate patient anatomical features with planning strategy using machine learning tools was unsuccessful, the resulting dosimetric outcomes proved satisfactory. Our algorithm consistently produced high-quality plans, offering significant time and efficiency advantages.

Use of Remote Sensing and Geographic Information System for the Analysis of Urban Development: A Case Study of Banyumas Regency, Indonesia

The change in land-use/land-cover (LULC) is one of the physical factors in urban development and the rapid growth in population has necessitates the need for space, driven by high socio-economic activities. Banyumas is a regency that had experienced rapid population growth in the last two decades, establishing an activity and service center in the Barlingmascakeb region. This rapid population growth has led to massive changes in LULC. Therefore, this study aimed to observe the changes in LULC in 2000 and 2020 to determine the direction of urban development in Banyumas Regency within 20 years. Multispectral classification with a Maximum Likelihood algorithm was used to extract LULC information from Landsat images. The changes obtained by crosstab analysis on the multispectral classification results were used as a reference to observe the direction of urban development. This procedure used four quadrants according to the cardinal directions and Standard Deviational Ellipse (SDE). The result showed that LULC in the forest class experienced the highest change of 142,584.3 km², accounting for 48%. Based on the increase in built-up land over 20 years, the direction of urban development according to the cardinal directions showed that the most dominant increase was in quadrant II (Southeast), which is 56.44% or 21.95 km². It was concluded that the direction of urban development was oriented toward the southeast.

Normalized Difference Vegetation Index (NDVI) marked reliable value of Ulu Muda Forest Reserve

Water resources must be preserved because they are vital for agricultural, industrial, and domestic use, especially in tropical forest regions. Given the importance of the Ulu Muda Forest Reserve to the Kedah state in sustaining paddy cultivation for the country, this study aimed to provide reliable forest classification method and produce Normalized Difference Vegetation Index-Maximum Likelihood Classification of forest density map for Ulu Muda Forest Reserve. Here, the study reports measurements of the satellite remote sensing index for the forest based the image date. The forest recorded NDVI index of 0.72 to 0.98 for high density, NDVI index of 0.61 to 0.71 for moderate and NDVI index of 0.26 to 0.60 for low density area. The index showed higher value, which is comparable with reports of other tropical forest elsewhere. The results were influenced using satellite remote sensing pre-processing, processing, and classification. As a result, based on the satellite image indices approach, upper threshold of the higher density, the forest can exhibit higher capability for sustaining its ecological and hydrological functions. Given that most of the tropical forest biome has sustained this threshold, forest management should be sustained at this state, and more measures should be taken for example increase of protection forest classification in Rancangan Pengurusan Hutan (RPH) that is one of yearly planning report in states of Peninsular Malaysia. In the meantime, Geographical Information System (GIS) capacity should be mandate looking forwards for more utilisation in mapping for planning and projection of forest resource management activities.

Bacterial structures and their associated ARGs in Shanghai subway air, China

The air in the metro or subway system, which is a major form of public transportation in many metropolises, contributes to the transmission of pathogenic microorganisms. In this study, 18 aerosol samples were collected from two typical Shanghai subway stations (A and B) in the summer, transition, and winter seasons. Bacterial communities and their associated antibiotic resistance genes (ARGs) were analyzed using shotgun metagenomic sequencing. Metagenomic analysis approaches and random forest classification were used to compare and screen the distribution of key target species and ARGs. Bacteria were the predominant microbial kingdom with a relative abundance of 88.28%. In total, 5303 bacterial species were identified in subway stations A and B. The top three abundant bacterial species were unclassified_Pseudomonas, Ewingella_americana, and Halalkalicoccus_subterraneus. Microbial diversity analysis revealed that the microbial communities significantly varied between the three seasons (P < 0.05). Additionally, factors, such as temperature, relative humidity, and fine particulate matter (PM2.5) significantly influenced bacterial community structure (P < 0.05). The random forest algorithm was used to screen indicators in bacterial communities. Some of these bacterial communities, which were primarily derived from environmental sources, may pose health risks. In total, 312 ARGs subtypes related to 20 ARGs classes were identified in subway stations A and B. Random forest classification results revealed 20 indicative types of ARGs, including those involved in metabolizing aminoglycoside, beta-lactam, multidrug, and rifamycin-type antibiotics. This study provides novel insights into microbial communities and ARGs in typical subway micro-environments and their dissemination in subway environments.

Evaluating a Novel Approach to Detect the Vertical Structure of Insect Damage in Trees Using Multispectral and Three-Dimensional Data from Drone Imagery in the Northern Rocky Mountains, USA

Remote sensing is a well-established tool for detecting forest disturbances. The increased availability of uncrewed aerial systems (drones) and advances in computer algorithms have prompted numerous studies of forest insects using drones. To date, most studies have used height information from three-dimensional (3D) point clouds to segment individual trees and two-dimensional multispectral images to identify tree damage. Here, we describe a novel approach to classifying the multispectral reflectances assigned to the 3D point cloud into damaged and healthy classes, retaining the height information for the assessment of the vertical distribution of damage within a tree. Drone images were acquired in a 27-ha study area in the Northern Rocky Mountains that experienced recent damage from insects and then processed to produce a point cloud. Using the multispectral data assigned to the points on the point cloud (based on depth maps from individual multispectral images), a random forest (RF) classification model was developed, which had an overall accuracy (OA) of 98.6%, and when applied across the study area, it classified 77.0% of the points with probabilities greater than 75.0%. Based on the classified points and segmented trees, we developed and evaluated algorithms to separate healthy from damaged trees. For damaged trees, we identified the damage severity of each tree based on the percentages of red and gray points and identified top-kill based on the length of continuous damage from the treetop. Healthy and damaged trees were separated with a high accuracy (OA: 93.5%). The remaining damaged trees were separated into different damage severities with moderate accuracy (OA: 70.1%), consistent with the accuracies reported in similar studies. A subsequent algorithm identified top-kill on damaged trees with a high accuracy (OA: 91.8%). The damage severity algorithm classified most trees in the study area as healthy (78.3%), and most of the damaged trees in the study area exhibited some amount of top-kill (78.9%). Aggregating tree-level damage metrics to 30 m grid cells revealed several hot spots of damage and severe top-kill across the study area, illustrating the potential of this methodology to integrate with data products from space-based remote sensing platforms such as Landsat. Our results demonstrate the utility of drone-collected data for monitoring the vertical structure of tree damage from forest insects and diseases.

Linking crown fire likelihood with post-fire spectral variability in Mediterranean fire-prone ecosystems

Background Fire behaviour assessments of past wildfire events have major implications for anticipating post-fire ecosystem responses and fuel treatments to mitigate extreme fire behaviour of subsequent wildfires. Aims This study evaluates for the first time the potential of remote sensing techniques to provide explicit estimates of fire type (surface fire, intermittent crown fire, and continuous crown fire) in Mediterranean ecosystems. Methods Random Forest classification was used to assess the capability of spectral indices and multiple endmember spectral mixture analysis (MESMA) image fractions (char, photosynthetic vegetation, non-photosynthetic vegetation) retrieved from Sentinel-2 data to predict fire type across four large wildfires Key results MESMA fraction images procured more accurate fire type estimates in broadleaf and conifer forests than spectral indices, without remarkable confusion among fire types. High crown fire likelihood in conifer and broadleaf forests was linked to a post-fire MESMA char fractional cover of about 0.8, providing a direct physical interpretation. Conclusions Intrinsic biophysical characteristics such as the fractional cover of char retrieved from sub-pixel techniques with physical basis are accurate to assess fire type given the direct physical interpretation. Implications MESMA may be leveraged by land managers to determine fire type across large areas, but further validation with field data is advised.

Remote Sensing Estimation of Forest Carbon Stock Based on Machine Learning Algorithms

Improving the precision of remote sensing estimation and implementing the fusion and analysis of multi-source data are crucial for accurately estimating the aboveground carbon storage in forests. Using the Google Earth Engine (GEE) platform in conjunction with national forest resource inventory data and Landsat 8 multispectral remote sensing imagery, this research applies four machine learning algorithms available on the GEE platform: Random Forest (RF), Classification and Regression Trees (CART), Gradient Boosting Trees (GBT), and Support Vector Machine (SVM). Using these algorithms, the entire Yunnan Province is classified into seven categories, including broadleaf forest, coniferous forest, mixed broadleaf-coniferous forest, water bodies, built-up areas, cultivated land, and other types. After a thorough comparison, the research reveals that the RF algorithm surpasses others in terms of accuracy and reliability, making it the most suitable choice for estimating aboveground carbon storage in forests using remote sensing data. Therefore, the study used the RF algorithm for both forest classification and the estimation of carbon storage. By extracting remote sensing factors; by using the Pearson correlation coefficient to select the most relevant factors; and by utilizing multiple linear regression, RF regression, and decision tree regression, a model for estimating aboveground carbon stocks in forests was developed. The results indicate that among the four classification algorithms, the RF classifier demonstrates superior performance, with an overall accuracy of 84.96% and a Kappa coefficient of 76.46%. In the RF regression models, the R2 values for the coniferous forest, broadleaf forest, and mixed needle-broadleaf forest models are 0.636, 0.663, and 0.638, respectively. In both RF and CART, the R2 values for the three forest-type models are greater than 0.6, indicating satisfactory model fitting performance. This study aims to explore the possibility of improving the estimation of forest carbon stocks in large-scale areas through fine land use classification. Additionally, the data sources used are completely free, and medium to low resolution can provide a better reference value for practical applications, thereby reducing the cost of utilization.

Adaptive Random Forest for Gait Prediction in Lower Limb Exoskeleton

To improve the human-machine cooperativity of a wearable lower limb exoskeleton, a gait recognition method based on surface electromyography (sEMG) was proposed. sEMG of rectus femoris, vastus medialis, vastus lateralis, semitendinosus and biceps femoris were acquired. Then, time domain, frequency domain, time-frequency domain and nonlinear features were extracted. The integrated value of electromyography, variance, root mean square and wavelength were selected as the time domain features and the frequency domain feature includes mean power frequency. Wavelet packet energy was selected as the time-frequency domain feature. Nonlinear features including approximate entropy, sample entropy and fuzzy entropy of sEMG were extracted. Classification accuracy of different feature matrices and different muscle groups were constructed and verified. The optimal multi-dimensional fusion feature matrix was determined. Introducing the Bayesian optimization algorithm, the Bayesian optimized Random Forest classification model was constructed to identify different gait phases. Comparing with Random Forest, the accuracy of the optimized Random Forest was improved by 5.89%. Applying Random Forest algorithm with Bayesian optimization to gait prediction based on sEMG, the followership and consistency of gait control in lower limb exoskeleton can be improved. This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text.

Using internal standards in time-resolved X-ray micro-computed tomography to quantify grain-scale developments in solid-state mineral reactions

Abstract. X-ray computed tomography has established itself as a crucial tool in the analysis of rock materials, providing the ability to visualise intricate 3D microstructures and capture quantitative information about internal phenomena such as structural damage, mineral reactions, and fluid–rock interactions. The efficacy of this tool, however, depends significantly on the precision of image segmentation, a process that has seen varied results across different methodologies, ranging from simple histogram thresholding to more complex machine learning and deep-learning strategies. The irregularity in these segmentation outcomes raises concerns about the reproducibility of the results, a challenge that we aim to address in this work. In our study, we employ the mass balance of a metamorphic reaction as an internal standard to verify segmentation accuracy and shed light on the advantages of deep-learning approaches, particularly their capacity to efficiently process expansive datasets. Our methodology utilises deep learning to achieve accurate segmentation of time-resolved volumetric images of the gypsum dehydration reaction, a process that traditional segmentation techniques have struggled with due to poor contrast between reactants and products. We utilise a 2D U-net architecture for segmentation and introduce machine-learning-obtained labelled data (specifically, from random forest classification) as an innovative solution to the limitations of training data obtained from imaging. The deep-learning algorithm we developed has demonstrated remarkable resilience, consistently segmenting volume phases across all experiments. Furthermore, our trained neural network exhibits impressively short run times on a standard workstation equipped with a graphic processing unit (GPU). To evaluate the precision of our workflow, we compared the theoretical and measured molar evolution of gypsum to bassanite during dehydration. The errors between the predicted and segmented volumes in all time series experiments fell within the 2 % confidence intervals of the theoretical curves, affirming the accuracy of our methodology. We also compared the results obtained by the proposed method with standard segmentation methods and found a significant improvement in precision and accuracy of segmented volumes. This makes the segmented computed tomography images suited for extracting quantitative data, such as variations in mineral growth rate and pore size during the reaction. In this work, we introduce a distinctive approach by using an internal standard to validate the accuracy of a segmentation model, demonstrating its potential as a robust and reliable method for image segmentation in this field. This ability to measure the volumetric evolution during a reaction with precision paves the way for advanced modelling and verification of the physical properties of rock materials, particularly those involved in tectono-metamorphic processes. Our work underscores the promise of deep-learning approaches in elevating the quality and reproducibility of research in the geosciences.

Differences in dissolved organic matter and analysis of influencing factors between plantations pure and mixed forest soils in the loess plateau

The dissolved organic matter (DOM) in forest ecosystems significantly impacts soil carbon cycling due to its active turnover characteristics. However, whether different plantation forest soil profiles exhibit distinct DOM characteristics remains unclear. Hence, utilizing fluorescence spectroscopy and the parallel factor analysis (PARAFAC) method, a 1-meter soil profile analysis was carried out on three distinct artificial forests (Pinus tabuliformis (PT), Quercus crispula (QC), and a mixed forest of PT and QC (MF)), concurrently assessing the impact of soil chemical properties and enzyme activity on dissolved organic matter (DOM). The findings indicated that the mean concentration of dissolved organic carbon (DOC) was greatest in the MF and lowest in PT, exhibiting considerable variation with soil depth, suggesting that mixed tree species may promote the discharge of organic matter. The fluorescence spectra revealed two distinct peaks: humic-like fluorescence peaks (Peaks A and C) and a protein-like fluorescence peak (Peak T), with the most intense fluorescence observed in MF soil. As the soil depth increased, the fluorescence intensity of Peaks A and C steadily declined, while the intensity of Peak T rose. Four DOM components were identified in three types of plantations forests: surface soil was dominated by humic acid-like fluorescent components (C1 and C2), while the deep soil was primarily characterized by protein-like fluorescence components (C3 and C4). Different soil profile fluorescence parameter indices indicated that the source of DOM in the surface soil (i.e., 0–20 cm) was mainly allochthonous inputs, whereas, in the deep soil (i.e., 60–100 cm), it was mainly autochthonous, such as microbial activity. The findings from the partial least squares path modeling (PLS-PM) revealed that TP, aP, NH4+-N, and the combined impact of soil enzymes were influential in shaping the diversity of DOM attributes. Put differently, alterations in DOM concentration were concomitantly influenced by forest classification, soil characteristics, and depth. It has been demonstrated that, in contrast to monoculture forests, the establishment of mixed forest models has been more advantageous in enhancing the soil dissolved organic matter (DOM). These discoveries offer innovative perspectives on the dynamic characteristics of DOM in soil profiles and its influencing factors under different plantations forest planting patterns.

A RANDOM FOREST-BASED MODEL OF SCORE FLUCTUATIONS IN PROFESSIONAL TENNIS MATCHES

In tennis matches, the victory and turning points of the game are often influenced by various factors. To explore the factors that affect match fluctuations (changes in the flow of scoring) and to provide suggestions for athletes match strategies, this paper first identifies general indicators through a literature review and uses logistic regression to determine the effectiveness of the chosen model. Secondly, it employs the Fourier function fitting to identify turning points in the match. Considering the scarcity of turning points in the game, this paper uses the SMOTE method to expand the dataset. Subsequently, it tests with a random forest classification model, achieving an accuracy of 93.433%. To improve the models accuracy, several indicators were added to the original model, resulting in a correct rate of 98.51%. Finally, to verify the models results and applicability, the model was applied to other matches with good results. A sensitivity analysis was conducted, revealing good model stability. The model results indicate that the main factors affecting the appearance of turning points include the players movement distance during the match, whether there are changes in the depth and width of the return, score differences, and the maximum number of consecutive wins. When tested in other types of matches, we found that the importance of these factors may change to some extent, but the results remain satisfactory. KEYWORDS: Volatility prediction, Random Forest, Logistic regression, Sensitivity analysis.

Passive acoustic data yields insights into bird vocalization behavior associated with invasive shrub removal

AbstractMonitoring biodiversity changes associated with ecological restoration is crucial in the current UN Decade on Restoration. Although several studies highlight the impacts of restoration on ecosystems, it is also important to understand how restoration alters species' behavior, including vocalization. Advances in conservation technology, such as passive acoustic monitoring, facilitate rapid and noninvasive monitoring. In this study, we quantified changes in the vocal behavior of a bird species in response to small‐scale restoration carried out by removing the invasive shrub, Lantana camara (lantana), in a Central Indian tropical dry forest. We examined associations between sites of varying lantana densities and the vocalization of one of its primary dispersers, red‐vented bulbul (RVBU). We found statistically significant differences in note‐length and bandwidth of RVBU vocalizations across sites. A random forest classification model showed that Lantana density was not an important predictor of RVBU vocalizations. Apart from the percentage of forest area and farms in our sites, total human population was the most important predictor for RVBU vocalizations suggesting RVBU's use of human habitations as possible resource hubs. Our findings suggest that lantana removal is not associated with significant changes in RVBU vocalization. This study provides empirical evidence that ecological restoration may not alter species' vocalization in the short term and highlights the importance of moving beyond species presence and understanding the impact of restoration on species behavior.

Machine Learning-Based Analysis Reveals Triterpene Saponins and Their Aglycones in Cimicifuga racemosa as Critical Mediators of AMPK Activation.

Cimicifuga racemosa (CR) extracts contain diverse constituents such as saponins. These saponins, which act as a defense against herbivores and pathogens also show promise in treating human conditions such as heart failure, pain, hypercholesterolemia, cancer, and inflammation. Some of these effects are mediated by activating AMP-dependent protein kinase (AMPK). Therefore, comprehensive screening for activating constituents in a CR extract is highly desirable. Employing machine learning (ML) techniques such as Deep Neural Networks (DNN), Logistic Regression Classification (LRC), and Random Forest Classification (RFC) with molecular fingerprint MACCS descriptors, 95 CR constituents were classified. Calibration involved 50 randomly chosen positive and negative controls. LRC achieved the highest overall test accuracy (90.2%), but DNN and RFC surpassed it in precision, sensitivity, specificity, and ROC AUC. All CR constituents were predicted as activators, except for three non-triterpene compounds. The validity of these classifications was supported by good calibration, with misclassifications ranging from 3% to 17% across the various models. High sensitivity (84.5-87.2%) and specificity (84.1-91.4%) suggest suitability for screening. The results demonstrate the potential of triterpene saponins and aglycones in activating AMP-dependent protein kinase (AMPK), providing the rationale for further clinical exploration of CR extracts in metabolic pathway-related conditions.

A comprehensive analysis and future projection of land use and land cover dynamics in a fast-growing city: A case study of Sekondi-Takoradi metropolis, Ghana

Sekondi-Takoradi is the most urbanized metropolis in the Western region of Ghana. Over the past two decades, it has experienced rapid shifts in both population density and land cover. Unfortunately, these transformations have significantly altered the natural landscape and expanded urban coverage. Previous studies have not established enough evidence on land use and land cover changes in the metropolis. For this reason, this study examined the existence, rate, and spatial distribution of land use and land cover as well as the future changes in land cover in the metropolis. Landsat imagery spanning from 1991, 2009, 2016, to 2023 provided the basis for evaluating the spatiotemporal dynamics of land use and cover within the metropolis. The Random Forest Classification algorithm was employed to categorize the images into three distinct classes: water, vegetation, and built-up areas. Analysis revealed a rapid growth in built-up areas by 63.08 km² (32.91 %), accompanied by a decrease in vegetation and water coverage by 60.99 km² (31.82 %) and 2.08 km² (1.09 %) respectively. This highlights the accelerating urbanization trend, emphasizing the critical need for vigilant monitoring and controlled urban expansion to mitigate potential adverse effects. Projections for 2030 indicate further changes with water areas decreasing to 1.21 km² (0.63 %), vegetation diminishing to 95.31 km² (49.73 %), and built-up areas expanding to 95.14 km² (49.64 %). This signifies a significant shift towards built-up areas, altering the metropolis' land cover composition and potentially impeding the achievement of Sustainable Development Goal 11. Understanding these changes in land use and land cover holds significant value for policymakers, enabling them to effectively monitor and safeguard natural resources.

Precipitation Estimation Using FY-4B/AGRI Satellite Data Based on Random Forest

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.

Development of Machine Learning Methods for Accurate Prediction of Plant Disease Resistance

The traditional method of screening plants for disease resistance phenotype is both time-consuming and costly. Genomic selection offers a potential solution to improve efficiency, but accurately predicting plant disease resistance remains a challenge. In this study, we evaluated eight different machine learning (ML) methods, including random forest classification (RFC), support vector classifier (SVC), light gradient boosting machine (lightGBM), random forest classification plus kinship (RFC_K), support vector classification plus kinship (SVC_K), light gradient boosting machine plus kinship (lightGBM_K), deep neural network genomic prediction (DNNGP), and densely connected convolutional networks (DenseNet), for predicting plant disease resistance. Our results demonstrate that the three plus kinship (K) methods developed in this study achieved high prediction accuracy. Specifically, these methods achieved accuracies of up to 95% for rice blast (RB), 85% for rice black-streaked dwarf virus (RBSDV), and 85% for rice sheath blight (RSB) when trained and applied to the rice diversity panel I (RDPI). Furthermore, the plus K models performed well in predicting wheat blast (WB) and wheat stripe rust (WSR) diseases, with mean accuracies of up to 90% and 93%, respectively. To assess the generalizability of our models, we applied the trained plus K methods to predict RB disease resistance in an independent population, rice diversity panel II (RDPII). Concurrently, we evaluated the RB resistance of RDPII cultivars using spray inoculation. Comparing the predictions with the spray inoculation results, we found that the accuracy of the plus K methods reached 91%. These findings highlight the effectiveness of the plus K methods (RFC_K, SVC_K, and lightGBM_K) in accurately predicting plant disease resistance for RB, RBSDV, RSB, WB, and WSR. The methods developed in this study not only provide valuable strategies for predicting disease resistance, but also pave the way for using machine learning to streamline genome-based crop breeding.

377 CDKN2A Alterations Are Associated With Increased Postoperative Seizure Risk After Resection of Brain Metastases

INTRODUCTION: Seizures are common and significantly disabling for patients with brain metastases (BMs). While surgical resection can provide seizure control, a subset of patients with BMs may continue to suffer seizures postoperatively. Molecular BM characteristics may influence which patients are at-risk for postoperative seizures. METHODS: All patients underwent BM resection at one institution with available clinical and sequencing data on &gt; 500 oncogenes. Clinical seizures were documented preoperatively and postoperatively. Random forest machine learning classification was used to determine candidate genomic alterations associated with postoperative seizures, and clinical and top genomic variables were correlated with postoperative seizures using Cox proportional hazards models. RESULTS: There were 112 patients with BMs who underwent 114 surgeries and had at least one month of postoperative follow-up. Seizures occurred preoperatively in 26 (22.8%) patients and postoperatively in 25 (21.9%). Engel classification (EC) at six months achieved for those with preoperative seizures was EC I in 13 (50%); II in 6 (23.1%); III in 5 (19.2%), and IV in 2 (7.7%). In those with postoperative seizures, only 8 (32.0%) had seizures preoperatively. Preoperative seizures were not a significant predictor of postoperative seizures (hazards ratio (HR) = 1.84; 95% confidence interval (CI) = 0.79 – 4.37; p = 0.156). On random forest classification and multivariate Cox analysis controlling for factors including recurrence, extent of resection, and number of BMs, CDKN2A alterations were associated with postoperative seizures (HR = 3.22; 95% CI = 1.27–8.16; p = 0.014). Melanoma BMs were associated with higher risk of postoperative seizures compared with all other malignancies (HR = 5.23; 95% CI = 1.37–19.98; p = 0.016). CONCLUSIONS: CDKN2A alterations and melanoma primary malignancy are associated with increased postoperative seizure risk following resection of BMs. These results may help guide postoperative seizure prophylaxis in patients undergoing resection of BMs.

SNIa DETECTION ANALYSIS RESULTS FROM REAL AND SIMULATED IMAGES USING SPECIALIZED SOFTWARE

The detection of transient events, Type Ia supernovae in particular, has become an important research subject in today's astronomy. We use as a base tool the software suite for astronomical image processing called LSSTsp and adapt it to assemble a type Ia supernova detection pipe. We study some straightforward changes on the overall pipeline by selecting better quality inputs to perform a coaddition of reference images, we analyze the different residual sources detected on the difference images and, lastly, we build light curves by taking into account the features of detected difference image analysis sources. Finally, we build a catalog of supernova candidates by using a random forest classification, and check the relevance these additions. We reduced the overall source detection density with our changes while finding between 82% and 85% of the present Type Ia supernovae.

Accurate species classification of Arctic toothed whale echolocation clicks using one-third octave ratios.

Passive acoustic monitoring has been an effective tool to study cetaceans in remote regions of the Arctic. Here, we advance methods to acoustically identify the only two Arctic toothed whales, the beluga (Delphinapterus leucas) and narwhal (Monodon monoceros), using echolocation clicks. Long-term acoustic recordings collected from moorings in Northwest Greenland were analyzed. Beluga and narwhal echolocation signals were distinguishable using spectrograms where beluga clicks had most energy >30 kHz and narwhal clicks had a sharp lower frequency limit near 20 kHz. Changes in one-third octave levels (TOL) between two pairs of one-third octave bands were compared from over one million click spectra. Narwhal clicks had a steep increase between the 16 and 25 kHz TOL bands that was absent in beluga click spectra. Conversely, beluga clicks had a steep increase between the 25 and 40 kHz TOL bands that was absent in narwhal click spectra. Random Forest classification models built using the 16 to 25 kHz and 25 to 40 kHz TOL ratios accurately predicted the species identity of 100% of acoustic events. Our findings support the use of echolocation TOL ratios in future automated click classifiers for acoustic monitoring of Arctic toothed whales and potentially for other odontocete species.