Rain Conditions Research Articles

Comparison of CNN-Based Models for Pothole Detection in Real-World Adverse Conditions: Overview and Evaluation

Potholes pose a significant problem for road safety and infrastructure. They can cause damage to vehicles and present a risk to pedestrians and cyclists. The ability to detect potholes in real time and with a high level of accuracy, especially under different lighting conditions, is crucial for the safety of road transport participants and the timely repair of these hazards. With the increasing availability of cameras on vehicles and smartphones, there is a growing interest in using computer vision techniques for this task. Convolutional neural networks (CNNs) have shown great potential for object detection tasks, including pothole detection. This study provides an overview of computer vision algorithms used for pothole detection. Experimental results are then used to evaluate the performance of the latest CNN-based models for pothole detection in different real-world road conditions, including rain, sunset, evening, and night, as well as clean conditions. The models evaluated in this study include both conventional and the newest architectures from the region-based CNN (R-CNN) and You Only Look Once (YOLO) families. The YOLO models demonstrated a faster detection response and higher accuracy in detecting potholes under clear, rain, sunset, and evening conditions. R-CNN models, on the other hand, performed better in the worse-visibility conditions at night. This study provides valuable insights into the performance of different CNN models for pothole detection in real road conditions and may assist in the selection of the most appropriate model for a specific application.

Experimental Study of the Effect of Humidity on Air Filter Material Performance

A large number of application cases show that air filter media are easy to fail under extreme conditions of high humidity, haze, rain and snow, thus seriously affecting the energy efficiency of gas turbines. To study the impact of humidity on the dust-holding performance of filter media, three typical filter media applied for gas turbines with a similar efficiency are selected, and their dust-holding performance is investigated at a humidity of 30%, 60% and 75%, respectively. The results showed that the dust-holding pressure drop curves of three filter media were divided into two phases. With the increase of humidity, the increasing pressure drop rate of three filter media decreased. The pressure drop synthetic fiber, glass fiber composite filter media and the synthetic fiber composite filter media with a sandwich structure were more significantly affected by humidity during the filter cake filtration phase. Under the same conditions, filter media with a sandwich structure had the highest dust-holding capacity, while the electrospun fiber composite filter material had the lowest one. The dustcake formed on the surface of the filter media that consist of a pure synthetic fiber or a small amount of plant fiber is significantly affected by humidity.

Evaluation of waterlogging tolerance and responses of protective enzymes to waterlogging stress in pumpkin.

Waterlogging caused by short and severe, or prolonged precipitation can be attributed to global warming. Pumpkin plants are drought-tolerant but not tolerate to waterlogging stress. Under frequent rain and waterlogging conditions, the production of pumpkins is of lower quality, sometimes rotten, and harvest failure occurs in severe cases. Therefore, it is of great significance to assess the waterlogging tolerance mechanism of pumpkin plants. In this study, 10 novel pumpkin varieties from Baimi series were used. The waterlogging tolerance level of pumpkin plants was evaluated by measuring waterlogging tolerance coefficient of biomass and physiological indices using waterlogging stress simulation method. The criteria to evaluate the waterlogging tolerance capacities of pumpkin plants were also explored. Using principal component and membership function analysis, waterlogging tolerance levels of the pumpkin varieties were ranked as follows: Baimi No. 10>; Baimi No. 5>; Baimi No. 1>; Baimi No. 2>; Baimi No. 3>; Baimi No. 7>; Baimi No. 9>; Baimi No. 6>; Baimi No. 4>; Baimi No. 8. Based on the results, Baimi No. 10 was identified with strong waterlogging tolerance and Baimi No. 8 with weak waterlogging tolerance. The responses of malondialdehyde (MDA), proline, key enzymes responsible for anaerobic respiration, and antioxidant enzymes to waterlogging stress were studied in pumpkin plants. The relative expression levels of related genes were determined using real-time fluorescence quantitative PCR technique. The aim of our study was to assess the waterlogging tolerance mechanism of pumpkin plants, thus laying a theoretical foundation for breeding waterlogging-tolerant varieties in the future. After flooding stress treatment, the antioxidant enzyme activities, contents of proline and alcohol dehydrogenases of Baimi No. 10 and Baimi No. 8 displayed an increase followed by a decrease. All indices of Baimi No. 10 were higher than Baimi No. 8. MDA contents gradually increased, with the content being higher in Baimi No. 8 than Baimi No. 10. The activities of pyruvate decarboxylases (PDCs) in Baimi No. 8 and Baimi No. 10 exhibited a decrease initially, followed by an increase, and then a decrease again. The PDC activity in Baimi No. 8 was generally higher than Baimi No. 10. The relative expression levels of genes encoding superoxide dismutase, peroxidase, catalase, and ascorbate peroxidase were consistent with their corresponding enzyme activities. During the early stage of flooding stress, pumpkin plants waterlogging tolerance was improved by enhancing the expression levels of antioxidant enzyme encoding genes and increasing the antioxidant enzyme activities.

Analysis and simulation of nitrogen loss during water erosion process on windward slope under wind-driven rain conditions

Wind-driven rain (WDR) is a common source of soil erosion in nature and usually occurs on windward slopes. This study investigated the effects of WDR events at different wind velocities of 0, 2, 3, 5, 7, 8 m s−1 and rainfall intensities of 30, 60, 90 mm h−1 on runoff, sediment yield, and total nitrogen (TN) loss processes on windward slopes. Additionally, the study constructed quantitative relationships between TN loss rate and simultaneous runoff and sediment using indoor simulated WDR experiments. The distributed soil erosion model KINEROS2 was then modified to embedded with these relationships, and used to simulate and verify the runoff, sediment yield, and TN loss processes during WDR events on windward slopes. The results showed an initial substantial increase followed by a gradual stabilization trend in runoff rates, sediment yield loss rates, and sediment-associated TN loss rates on windward slopes. As wind velocity increased from 0 to 8 m s−1 under a rainfall intensity of 90 mm h−1, the average runoff rate, sediment yield rate, and sediment-associated TN loss rate decreased linearly by 4.30%–16.13%, 9.82%–34.44%, and 14.54–46.42%, respectively. However, runoff-associated TN loss rate increased in a linear trend of 26.49%–137.59%. Similar trends were observed at rainfall intensities of 30 and 60 mm h−1. When simulated using the KINEROS2 and nitrogen migration model embedded with mathematical relationships between wind velocity and soil erosion and TN loss on windward slopes, the NSE and R2 of runoff, sediment, and TN loss processes were 0.49–0.83 and 0.59–0.89, 0.21–0.82 and 0.42–0.88, and 0.21–0.73 and 0.38–0.83, respectively. This study provides insights into the effects of WDR events on TN loss at plot scale and offers guidance for KINEROS2 application under WDR conditions at different slope directions and watershed scales.

Predicting the performance of radio over free space optics system using machine learning techniques

The efficiency and reliability of radio over free space optical communication may be significantly degraded by different weather conditions, thus leading to decrease and increase of signal to noise ratio (SNR) and bit error rate (BER) of the recovered signal respectively. Therefore, real time optical performance estimation is of utmost importance to enable the awareness of channel conditions and for achieving high quality of service. In this work, a terrestrial radio over free space optics (RoFSO) system has been investigated by employing 32-QAM and 64-QAM OFDM modulation schemes under rain, haze and clear weather conditions. Performance of the system is further estimated by employing artificial neural networks (ANN), k-nearest neighbours (KNN) and decision tree (DT) machine learning (ML) techniques with root mean square error (RMSE) and coefficient of determination (R2) as performance metrices. Atmospheric attenuation and different internal system parameters act as input features with BER and SNR of the received signal as the modelling targets. The best performing model has been found to be by applying an ANN approach with lower RMSE values for SNR and BER as 1.87 and 1.26 respectively. The value of R2 predicted by the model are 0.97139 and 0.97802 for SNR and BER data sets respectively.

Study of Morphology and Corrosion Behavior of Aluminum Coatings on Steel Substrates under Simulated Acid Rain Conditions

In this paper, aluminum coatings were prepared on a steel substrate by thermal spraying, and the corrosion morphology and corrosion resistance of the coating were investigated by salt spray and immersion tests. The results showed that after three months of salt spray tests, the coating still exhibited a surface morphology without significant damage and had good damage tolerance. Further effective protection of the substrate can be achieved by spraying the coating surface with paint. After three months of immersion test, the corrosion rate of samples with thicker coatings was located between 0.002 mm/y and 0.005 mm/y, and only a small amount of corrosion products was observed on the coating surface. The coated samples after salt spray and immersion tests maintained sufficient adhesion (17.07 MPa and 19.25 MPa), and the surface aluminum coating was highly reliable for protection of the steel substrate. In general, the reliability of the coating can be further improved by painting the surface of the thicker Al coating. This provides more ideas for the protection of transmission and transformation equipment.

Measurement, Evaluation, and Performance of 60 Gbps DPSK WDM Free Space Optical Link for Haze and Rain Conditions

Measurement, Evaluation, and Performance of 60 Gbps DPSK WDM Free Space Optical Link for Haze and Rain Conditions

KAJIAN PENGGUNAAN CULTIVATOR TIPE MOTOYAMA MTE 70NL UNTUK PENGOLAHAN TANAH DI LAHAN KELOMPOK TANI SYALOM DESA PINASUNGKULAN KECAMATAN MODOINDING

ABSTRACTThe Cultivator Motoyama MTE 70NL is an agricultural tool and machine provided by theGovernment of South Minahasa Regency for farmer groups in Modoinding District, for thedevelopment of upland projects. This cultivator is used for secondary tillage. Meanwhile, it isnecessary to know the performance of the tools distributed to farmers, so a study is needed tounderstand how the performance of the Motoyama MTE 70NL cultivator is like for tillage bothin conditions without rain and in rainy conditions. Rain conditions are used as a parameter tocompare cultivator performance with conditions without rain. In the treatment of soil conditionsafter rain, the calculation of rainfall is not carried out, even so after the rain is adjusted to the soilconditions, if the soil is too wet, it will be waited until the soil conditions can be processed. Thepurpose of this study was to analyze the performance of the Motoyama MTE 70NL typecultivator for tillage in 2 treatments, namely treatment 1 on soil conditions without rain andtreatment 2 on soil conditions after rain. The area of research land used is 5m x 30m on a flatexpanse. The variables observed in this study include: depth of tillage layer, speed, workingwidth of the tool, travel time, head land, fuel oil, and tool rpm. The results of this study indicatethat tillage using the Motoyama MTE 70NL cultivator in the first treatment resulted in a traveltime of 12.49 minutes, a head land of 49 seconds, fuel oil 213.14 ml, a depth of tillage layer of30 cm. In the two treatments, the travel time was 13.13 minutes, the head land was 50 seconds,the fuel oil was 219 ml, and the depth of the tillage layer was 30 cm. The engine RPM is 2,416.2r/min and the slow rotary gear rpm is 74.4 r/min. In treatment 1 KLT 0.074 ha/hour, KLE 0.071ha/hour, EL 95.94%. In treatment 2 KLT 0.074 ha/hour, KLE 0.069 ha/hour, EL 93.24%.Keywords: Cultivator, Soil Processing

High-Precision AI-Enabled Flood Prediction Integrating Local Sensor Data and 3rd Party Weather Forecast

Flooding risk is a threat to many sea-level cities and residential areas in the world. In the city Kristianstad in southern Sweden, a large number of sensors of different types have been deployed to monitor rain and other weather conditions, water levels at sea and lakes, ground water levels, and water flows in the city's storm-water and sewage systems. All the sensors are enabled by battery and wireless communication, and allow real-time data to be transferred and visualized on a cloud-based Internet of Things (IoT) portal. To better enable the system with capacity of foreseeing upcoming flooding threats and to allow early response from decision-makers, it is desired to build a real-time flood forecast system by utilizing the massive sensor data collected at the IoT portal and data from 3rd party weather forecast service. In this article, we have developed a smart flood forecast system using machine learning and artificial neural networks. The developed forecast system has successfully integrated data from multiple sources and can make accurate flood forecast at distributed locations for the coming days. After being successfully implemented as software product and integrated with the city's IoT portal, our developed flood forecast system has significantly extended the basic monitoring functions of the city's IoT infrastructure. This article presents the context of this work, the challenges that have been encountered during our development, our solutions and performance evaluation results. To the best of our knowledge, this is the first large-scale IoT-based real-time flood forecast system that has been enabled by artificial intelligence (AI) and deployed in real world.

Performance Investigation of Generalized Rain Pattern Absorption Attention Network for Single-Image Deraining

Rainy weather conditions are challenging issues for many computer vision applications. Rain streaks and rain patterns are two crucial environmental factors that degrade the visual appearance of high-definition images. A deep attention network-based single-image deraining algorithm is more famous for handling the image with the statistical rain pattern. However, the existing deraining network suffers from the false detection of rain patterns under heavy rain conditions and ineffective detection of directional rain streaks. In this paper, we have addressed the above issues with the following contributions. We propose a multilevel shearlet transform-based image decomposition approach to identify the rain pattern on different scales. The rain streaks in various dimensions are enhanced using a residual recurrent rain feature enhancement module. We adopt the Rain Pattern Absorption Attention Network (RaPaat-Net) to capture and eliminate the rain pattern through the four-dilation factor network. Experiments on synthetic and real-time images demonstrate that the proposed single-image attention network performs better than existing deraining approaches.

Weather Conditions and Telematics Panel Data in Monthly Motor Insurance Claim Frequency Models

Risk analysis in motor insurance aims to identify factors that increase the frequency of accidents. Telematics data is used to measure behavioural information of drivers. Contextual variables include temperature, rain, wind and traffic conditions that are external to the driver, but may also influence the probability of having an accident, as well as vehicle and personal characteristics. This paper uses a monthly panel data structure and the Poisson model to predict the expected frequency of claims over time. Some meteorological information is included. Two types of claims are considered separately: only those related to at-fault third-party liability accidents, and all types of claims including assistance on the road. A sample of drivers in Spain in 2018–2019 is analysed with information on claiming frequency per month. Drivers were observed for seven months. Our analysis is novel because monthly summaries of telematics information are combined with weather data in a panel structure, revealing that external factors affect the expected claims frequencies. Reckless speeding behaviours and intense urban circulation increase the risk of an accident, which also increases with windy conditions.

Extreme Rainfall Event Classification Using Machine Learning for Kikuletwa River Floods

Advancements in machine learning techniques, availability of more data sets, and increased computing power have enabled a significant growth in a number of research areas. Predicting, detecting, and classifying complex events in earth systems which by nature are difficult to model is one such area. In this work, we investigate the application of different machine learning techniques for detecting and classifying extreme rainfall events in a sub-catchment within the Pangani River Basin, found in Northern Tanzania. Identification and classification of extreme rainfall event is a preliminary crucial task towards success in predicting rainfall-induced river floods. To identify a rain condition in the selected sub-catchment, we use data from five weather stations that have been labeled for the whole sub-catchment. In order to assess which machine learning technique is better suited for rainfall classification, we apply five different algorithms in a historical dataset for the period of 1979 to 2014. We evaluate the performance of the models in terms of precision and recall, reporting random forest and XGBoost as having the best overall performances. However, because the class distribution is imbalanced, a generic multi-layer perceptron performs best when identifying heavy rainfall events, which are eventually the main cause of rainfall-induced river floods in the Pangani River Basin.

SWEET: A Realistic Multiwavelength 3D Simulator for Automotive Perceptive Sensors in Foggy Conditions

Improving the reliability of automotive perceptive sensors in degraded weather conditions, including fog, is an important issue for road safety and the development of automated driving. Cerema has designed the PAVIN platform reproducing fog and rain conditions to evaluate optical automotive sensor performance under these conditions. In order to increase the variety of scenarios and technologies under test, the use of digital simulation becomes a major asset. The purpose of this paper is to revive the debate around the realism of the various models underlying the numerical methods. The simulation of the radiative transfer equation by Monte Carlo methods and by simplified noise models is examined. The results of this paper show some gaps in foggy scenes between the ray-tracing method, which is considered to be the most realistic, and simple models for contrast evaluation, which can have a particularly strong impact on obstacle detection algorithms.

Experimental and numerical research on the hydrological characteristics of sunken green space with a new type of composite structure.

Based on the characteristics of concentrated rainwater runoff in the mountainous areas of southwestern China and the low rates of rainwater infiltration into low-permeability soils. We have built a new type of sunken green space structure with a combination of a "overflow port and rainwater storage layer" and carried out model tests of storage and drainage performance under heavy rain conditions. The hydrological response of the new composite structure parameters to the sunken green space was analyzed using the HYDRUS-2D program. The results show that the new composite structure has a significant impact on runoff reduction, drainage, and rainwater storage. For the 100a return period, compared with RSL-0 (0cm rainwater storage layer), the initial and peak drainage times of RSL-25 were delayed by 30min and 38min, respectively, and the rainwater storage rate increased by 13.5%. Compared with no overflow port, the peak drainage increased by 78%, the initial drainage time advanced by 73min, and the cumulative drainage volume increased by 186%. In addition, as the height of the overflow increased, the surface rainwater absorbed by the sunken green space gradually decreased. The sunken green space with OPH-5 (overflow port height of 5cm) could absorb more than 75% of the rainwater in the rainwater overflow layer, while the absorption capacities of OPH-7.5 and OPH-10 (overflow port height of 7.5cm and 10cm) were basically below 75%. In this case, the OPH-5 and the depth of the storage layer not being less than 250cm provide the best setting for the new combined structure of the sunken green space. In conclusion, the new composite structure designed in this experiment effectively increased the hydrological performance of the layered sunken green space.

Investigation of moss species selection and substrate for extensive green roofs

This study investigates the potential of moss species for extensive green roofs to achieve very shallow substrate, low maintenance and low cost green roofs. The performance of four moss species (Didymodon constrictus, Eurhynchium hians, Polytrichum commune and Racomitrium japonicum) were assessed using three kinds of substrate: (a) a mixture of clay soil and compost, b) baked black soil and c) river sand for two years in Chiba, within the Tokyo region of Japan. The individual species were grown in monoculture in 4 cm depth of substrate in trays on a rooftop without supplemental irrigation using an onsite propagation method. Although all four species became dormant in conditions of high temperature and little rain, it was possible for all to establish and survive. R. japonicum showed the greatest coverage among the four species, reaching 70%–80% cover in the first four months. P. commune performed almost as well but took over a year to reach consistently high coverage. E. hians coverage fluctuated greatly in response to drought events. D. constrictus had low coverage overall but grew slightly more in the clay/compost soil; P. commune did poorly in sand substrate; R. japonicum and E. hians showed no consistent differences in how they were affected by substrate type. After two years only R. japonicum and P. commune had high enough coverage to consider further investigation. R. japonicum is already used in green roofing and wall applications. This study suggests that while some mosses show high performance across substrate types, others can be used on green roofs to achieve high cover, but only after determining a suitable substrate type. These results can inform moss species selection for green roofs in Japan, however, this methodology can be applied in other regions to establish moss green roofs. An onsite propagation method can be used to establish moss green roofs but further research is needed to identify means of increasing onsite growth rates for more species.

Investigation of Point Refractivity Gradient and Geoclimatic Factor at 70 m Altitude in Yenagoa, Nigeria

The quality of services provided via Inter-Terrestrial radio communication links such as GSM networks, Wide Area Network (WAN), Radio and TV broadcasts is largely influenced by some meteorological parameters such as temperature, pressure and humidity. Proper knowledge of these parameters, specifically at microwave antenna heights (about 70m) is important in order to maintain an effective line-of-sight (LOS) link even during the worst weather conditions. The geoclimatic factor is an important quantity that must be considered in the design of terrestrial links for effective wireless communication. This work utilized satellite data from the European Center for Medium-Range Weather Forecasts (ECMWF) to compute the point refractivity gradient and geoclimatic factor for Yenagoa and its environs. The research was necessitated by the paucity of research on this subject matter for Yenegoa. The results of the research show that point refractivity gradient and geoclimatic factor in the study area vary with season. The average point refractivity gradient and geoclimatic factor at 70 m above the ground level are:136.433 N-unit/Km and 6.638633E-05 respectively. This implies that radiowaves propagating in this region at the said altitude is most likely to be super refractive in both rain and clear air atmospheric conditions. Rain or worst condition refers to the period when atmospheric components such as hydrometeor, lithometeor, aerosol have significant effects on propagated radio signals. Clear-air conditions means when maximum possible signal is received such that the most threatening atmospheric components (rain drops) have negligible effects on propagated signal. The results will be useful for radio engineers in the design and configuration of inter-terrestrial microwave links in Yenagoa and Its environs for optimum quality of service.

Test Study of the Bridge Cable Corrosion Protection Mechanism Based on Impressed Current Cathodic Protection

The cable system is an important bearing element of a bridge with stay cables or slings and a matter of major concern in the safety of the bridge structure. Bridge cables are vulnerable to corrosion induced by leakage and soaking during their service life. To solve this problem, and based on the idea of proactive control by means of the impressed current cathodic protection (ICCP) of bridge cables, this study designs and develops an ICCP system device for bridge cable protection. In this study, an accelerated corrosion test was conducted to test the ICCP system of steel wires inside the cables and the cables under acid rain conditions. The corrosion protection behavior of ICCP was analyzed to reveal the corrosion protection mechanism of bridge cable ICCP. The results show that in the cable ICCP system, the impressed current generated by a more negative voltage may improve the efficiency of corrosion protection, but an excessively negative voltage may cause hydrogen embrittlement of the cable steel wire due to overprotection. The rational range of −1.13 V to −1.15 V was set as the result of the overall consideration. Within this range, the cable is subject to the joint protection of ICCP and sacrificial anode cathodic protection (SACP). Corrosive products can delay the development of cable corrosion to a certain degree; the SACP protection efficiency of the galvanized coat reduces gradually with corrosion development; and cable ICCP protection efficiency increases gradually. The ICCP for cable corrosion protection is transformed from joint protection using both a sacrificial anode and impressed current into protection, mainly using an impressed current.

Practical wheel/rail tangential contact force model for vehicle dynamics analysis combining Levi-Chartet’s formula with adhesion coefficient-velocity relational expression

This paper describes a practical wheel/rail tangential contact force model for railway dynamics analysis under running in rainy conditions. In our previous studies, it was confirmed that experimental results of tangential contact force measurement are agree well with Kalker’s rolling contact theory under dry condition with low humidity around contact surfaces. Here, it can be considered that if the ambient humidity around the contact surface become high infinity, the contact surface is under wet lubrication conditions. On the basis of this assumption, in this study, a practical estimation model for characteristics of tangential contact force under running in rainy conditions is proposed by combining the relationship between the adhesive coefficient and velocity measured on running experiments using actual railway vehicles and Kalker’s linear rolling contact theory. Therefore, to verify the proposed model, the tangential contact force measurement experiment using a twin-disk rolling sliding machine was carried out. As a result, it is confirmed that estimated formulae based on the proposed model are well agreed with experimental results even under different velocity conditions, comparing the relationship between tangential contact force coefficient and slip ratio. From these verified results, the proposed model is considered to be a practical wheel/rail tangential contact force model for vehicle dynamics analysis under rain conditions, because the proposed model has the advantage of low calculation cost and can be easily applied to vehicle dynamics analysis based on multi-body dynamics theories.

Explication of mechanism governing atmospheric degradation of 3D-printed poly(lactic acid) (PLA) with different in-fill pattern and varying in-fill density.

With the popularity of 3D-printing technology, poly(lactic acid) (PLA) has become a very good option for layer by layer printing as it is easy to handle, environment friendly, has low costs and most importantly, it is highly adaptable to different materials including carbon, nylon and some other fibres. PLA is an aliphatic poly-ester that is 100% bio-based and is bio-degradable as well. It is one of the rare bio-polymers to compete with traditional polymers in terms of performance and environmental impact. However, PLA is sensitive to water and susceptible to degradation under natural conditions of ultra-violet rays (UV), humidity, fumes, etc. There are many reports on the bio-degradation and photo-degradation of PLA which deal with the accelerated weathering test. However, the accelerated weathering test instruments lack the ability to correlate the stabilities maintained by the test with the actual occurrences during natural exposure. Thus, an attempt has been made in the present work to expose the 3D-printed PLA samples to actual atmospheric conditions of Aurangabad city (M.S.) in India. The degradation of PLA after the exposure is studied and a mechanism is elucidated. Additionally, the tensile properties of the PLA samples are evaluated to correlate the extent of degradation and the material performance. It was found that though the performance of PLA deteriorates with the exposure time, the combination of in-fill pattern and volume plays an important role on the tensile properties and the extent of degradation. It is concluded herein that with natural exposure, the degradation of PLA occurs in two stages, supported by a side reaction. Thus, this study offers a new perspective towards the life of components in actual application by exposing PLA to the natural atmosphere and evaluating its strength and structure.

Flushing or mixing? Stable water isotopes reveal differences in arctic forest and peatland soil water seasonality

AbstractUnderstanding the relative importance of different water sources that replenish soil water storage is necessary to assess the vulnerability of sub‐arctic areas to changes in climate and altered rain and snow conditions, reflected in the timing and magnitude of water infiltration. We examine spatiotemporal variability and seasonal origin of soil water at the soil‐vegetation interface in Pallas catchment, located in northern Finland. The field study was conducted from May 2019 to June 2020 over two snowmelt seasons and one summer growing season. We sampled soil cores up to a 1‐m depth and stem water of dominant tree species at four sites located in forests and forested peatlands for stable water isotopes. Seasonal rainfall variation and late snowmelt events were well identifiable in the well‐drained soils of forested areas, while this input signal is heavily attenuated in wetter, forested peatland areas. Spatiotemporal variability of soil water in two forest sites was similar, whereas soil water storage in peatland sites was controlled by the extent of hydrologic connectivity to the adjoining water pools. A mixture of both summer and winter precipitation was present in peatlands during the entire study period, while forest mineral soils showed an ephemeral response to water input and got nearly fully flushed twice during the hydrological year. Meltwater signal in forest soils was dominant after snowmelt and in early spring but became displaced by isotopically enriched rainfall during the summer. Seasonal evolution of soil water pools was not reflected in tree stem dynamics but offset between soil and stem water isotopic signals was less pronounced in forested peatlands. This field data set uncovered seasonal changes of soil water isotopic signal at high depth‐resolution, quantifying the importance of snowmelt water in replenishing and sustaining soil water storage in sub‐arctic conditions.