Land surface temperature (LST) is a critical parameter for characterizing surface energy balance and hydrothermal processes. While Landsat provides invaluable LST observations at medium spatial resolution for over 40 years, its native spatial resolution of thermal bands (e.g., 100 m) remains insufficient compared to its 30 m optical bands, failing to meet the demands of fine-scale studies. To address this issues, this study proposes a progressive self-training framework for downscaling Landsat LST to 30 m without relying on fine-scale ground truth, while maintaining minimal data dependence. The framework progressively optimizes a cross-modal fusion network to refine thermal details in a coarse-to-fine manner, characterized by one pre-training and two fine-tuning stages. Spatial validation against SDGSAT-1 30 m LST and temporal validation using in situ measurements confirm its reliability and accuracy, with both station-averaged MAE and RMSE outperforming the official cubic product by approximately 0.4 K. Further performance comparison experiments demonstrate that the proposed framework consistently reconstructs coherent fine-scale thermal patterns while preserving spatial heterogeneity. Multi spatial resolution evaluations and ablation studies verify the effectiveness of the proposed strategy and network design. Overall, the framework provides a stable pathway for enhancing the spatial resolution of Landsat LST, providing fine-resolution data support for fine-scale surface process studies and localized environmental monitoring.
The intensification of the urban heat island (UHI) effect poses a serious threat to public health, particularly in cities. Effectively mitigating UHI has been a focus of national and international academic research over the last decades. However, most contemporary research has focused on land use mitigation measures within urban areas, with less emphasis on suburban land use. To address this research gap and explore spatial characteristics, we analyzed the driving mechanism of suburban land use patterns on UHI intensity (UHII) within the main urban area of Shenyang City based on high spatial resolution raster data, such as Landsat remote sensing images and land use, combined with extreme gradient boosting and SHapley Additive exPlanations models. The landscape fragmentation index of overall suburban land use provided a stronger contribution to the UHII in urban areas than the aggregation index. Increased cropland fragmentation and aggregation enhance UHII mitigation, whereas increased aggregation of impervious surfaces intensifies UHII. No significant difference was observed between the effects of various suburban gradient landscapes on UHII; however, the effects on different gradients in urban areas increased with decreasing distance from the countryside, with a minimal effect observed on the extreme center of the city (U1). The study provides a theoretical reference for mitigating land use pressure and reducing the UHI in urban areas based on suburban land use.
The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing low-resolution or obsolete products. In this paper, we address the problem of training land-cover classifiers using high-resolution imagery (e.g., Sentinel-2) and weak low-resolution reference data (e.g., MODIS -derived land-cover maps). Inspired by recent works in Deep Multiple Instance Learning (DMIL), we propose a method that trains pixel-level multi-class classifiers and predicts low-resolution labels (i.e., patch-level classification), where the actual high-resolution labels are learned implicitly without direct supervision. This is achieved with flexible pooling layers that are able to link the semantics of the pixels in the high-resolution imagery to the low-resolution reference labels. Then, the Multiple Instance Learning (MIL) problem is re-framed in a multi-class and in a multi-label setting. In the former, the low-resolution annotation represents the majority of the pixels in the patch. In the latter, the annotation only provides us information on the presence of one of the land-cover classes in the patch and thus multiple labels can be considered valid for a patch at a time, whereas the low-resolution labels provide us only one label. Therefore, the classifier is trained with a Positive-Unlabeled Learning (PUL) strategy. Experimental results on the 2020 IEEE GRSS Data Fusion Contest dataset show the effectiveness of the proposed framework compared to standard training strategies.
For precise, efficient, and safe drone landings, ground platforms should real-time, accurately locate descending drones and guide them to designated spots. While mmWave sensing combined with cameras improves localization accuracy, the lower sampling frequency of traditional frame cameras compared to mmWave radar creates bottlenecks in system throughput. In this work, we replace the traditional frame camera with event camera, a novel sensor that harmonizes in sampling frequency with mmWave radar within the ground platform setup, and introduce mmE-Loc, a high-precision, low-latency ground localization system designed for drone landings. To fully leverage the \textit{temporal consistency} and \textit{spatial complementarity} between these modalities, we propose two innovative modules, \textit{consistency-instructed collaborative tracking} and \textit{graph-informed adaptive joint optimization}, for accurate drone measurement extraction and efficient sensor fusion. Extensive real-world experiments in landing scenarios from a leading drone delivery company demonstrate that mmE-Loc outperforms state-of-the-art methods in both localization accuracy and latency.
Aim of the study:
The purpose of the study is to substantiate the conceptual approaches of the complex and to consider its main components regarding the restoration of territories affected by the war in Ukraine, with an emphasis on the incompleteness of current legal acts. It is therefore essential to develop new legal mechanisms that will ensure the procedure for removing contaminated lands into state ownership for their long-term restoration, with appropriate compensation to landowners for the period of time that the contaminated land remains in state ownership.
Material and methods:
The theoretical basis consists of academic research by domestic and international scientists in the field of land management and environmental protection, legislative and regulatory acts, methodological and instructional materials, statistical and analytical data of ministries and departments of Ukraine, as well as public organizations regarding the use of land resources and socio-economic development of the regions of Ukraine. Methods used include: monographic analysis; synthesis method; structural and logical method; systemic approach; dialectical principle of connection /interaction.
Results and conclusions:
The land relations during the reconstruction of Ukraine should be based on the following principles and approaches: openness of the public cadastral map of Ukraine; simplification of permit procedures; assessment of land and soil quality, inventory; continuation of the trend of decreasing arable land; conservation of lands, the use of which could harm human life and health as well as the state of the environment; expropriation of land from tenants who are connected to Russia or Belarus; soil conservation in the context of war; introduction of the state system for the control of land resources and the responsibility of land users.
H. Patrick Roberts, Lori Erb, Lisabeth Willey
et al.
Turtle populations are declining globally, yet limited attention has been directed toward understanding the conservation status of species perceived to be widespread and common. The goal of this study was to contribute to the understanding of the conservation status of the eastern box turtle (Terrapene carolina), a wide-ranging terrestrial generalist, in the northeastern United States (Maine to Virginia) by (1) characterizing relationships between occurrence and anthropogenic land use and (2) estimating the extent of land-use driven habitat impairment for the region. We used a regional dataset of occurrence records combined with pseudo-absences to develop species distribution models to first estimate the potential distribution in the northeastern United States and then predict habitat suitability within that distribution. We observed a strong positive relationship between probability of occurrence and canopy cover (within 180 m) and a strong negative relationship with hay/pasture fields (360 m), cultivated crops (180 m), impervious surface (360 m), and forest loss (since 2000; 1440 m). We estimate that approximately 51% of eastern box turtle habitat in the northeastern United States may be impaired by land use, with the majority of impairment predicted from Pennsylvania and Delaware south to Virginia. This study, in combination with previous long-term studies documenting population declines, suggests that greater attention to the conservation status of the eastern box turtle is warranted.
There are various desired capabilities to create aerial forest-traversing robots capable of monitoring both biological and abiotic data. The features range from multi-functionality, robustness, and adaptability. These robots have to weather turbulent winds and various obstacles such as forest flora and wildlife thus amplifying the complexity of operating in such uncertain environments. The key for successful data collection is the flexibility to intermittently move from tree-to-tree, in order to perch at vantage locations for elongated time. This effort to perch not only reduces the disturbance caused by multi-rotor systems during data collection, but also allows the system to rest and recharge for longer outdoor missions. Current systems feature the addition of perching modules that increase the aerial robots' weight and reduce the drone's overall endurance. Thus in our work, the key questions currently studied are: "How do we develop a single robot capable of metamorphosing its body for multi-modal flight and dynamic perching?", "How do we detect and land on perchable objects robustly and dynamically?", and "What important spatial-temporal data is important for us to collect?"
Eduardo Moya-Lasheras, Edgar Ramirez-Laboreo, Carlos Sagues
The impact forces during switching operations of short-stroke actuators may cause bouncing, audible noise and mechanical wear. The application of soft-landing control strategies to these devices aims at minimizing the impact velocities of their moving components to ultimately improve their lifetime and performance. In this paper, a novel approach for soft-landing trajectory planning, including probability functions, is proposed for optimal control of the actuators. The main contribution of the proposal is that it considers uncertainty in the contact position and hence the obtained trajectories are more robust against system uncertainties. The problem is formulated as an optimal control problem and transformed into a two-point boundary value problem for its numerical resolution. Simulated and experimental tests have been performed using a dynamic model and a commercial short-stroke solenoid valve. The results show a significant improvement in the expected velocities and accelerations at contact with respect to past solutions in which the contact position is assumed to be perfectly known.
Anil Kokaram, Vibhoothi Vibhoothi, Julien Zouein
et al.
Virtual Production (VP) technologies have continued to improve the flexibility of on-set filming and enhance the live concert experience. The core technology of VP relies on high-resolution, high-brightness LED panels to playback/render video content. There are a number of technical challenges to effective deployment e.g. image tile synchronisation across the panels, cross panel colour balancing and compensating for colour fluctuations due to changes in camera angles. Given the complexity and potential quality degradation, the industry prefers "pristine" or lossless compressed source material for displays, which requires significant storage and bandwidth. Modern lossy compression standards like AV1 or H.265 could maintain the same quality at significantly lower bitrates and resource demands. There is yet no agreed methodology for assessing the impact of these standards on quality when the VP scene is recorded in-camera. We present a methodology to assess this impact by comparing lossless and lossy compressed footage displayed through VP screens and recorded in-camera. We assess the quality impact of HAP/NotchLC/Daniel2 and AV1/HEVC/H.264 compression bitrates from 2 Mb/s to 2000 Mb/s with various GOP sizes. Several perceptual quality metrics are then used to automatically evaluate in-camera picture quality, referencing the original uncompressed source content through the LED wall. Our results show that we can achieve the same quality with hybrid codecs as with intermediate encoders at orders of magnitude less bitrate and storage requirements.
This paper examines speakers’ systematic errors while speaking English as a foreign language (EFL) among students in Arab countries with the purpose of automatically recognizing and correcting mispronunciations using speech recognition, phonological features, and machine learning. Accordingly, three main steps are implemented towards this purpose: identifying the most frequently wrongly pronounced phonemes by Arab students, analyzing the systematic errors these students make in doing so, and developing a framework that can aid the detection and correction of these pronunciation errors. The proposed automatic detection and correction framework used the collected and labeled data to construct a customized acoustic model to identify and correct incorrect phonemes. Based on the trained data, the language model is then used to recognize the words. The final step includes construction samples of both correct and incorrect pronunciation in the phonemes model and then using machine learning to identify and correct the errors. The results showed that one of the main causes of such errors was the confusion that leads to wrongly utilizing a given sound in place of another. The automatic framework identified and corrected 98.2% of the errors committed by the students using a decision tree classifier. The decision tree classifier achieved the best recognition results compared to the five classifiers used for this purpose.
Social Sciences, Management. Industrial management
Syakur Syakur*, Sugianto Sugianto, Hairul Basri
et al.
The existence of forest park areas plays an essential role as carbon sequestration can reduce the concentration of greenhouse gases in the atmosphere. Analysis of carbon potential is essential in determining the amount of available carbon potential. This study aims to analyze the carbon potential in the forest park area Pocut Meurah Intan Forest Park. The study used a descriptive method with the sampling technique of the path system. Data analysis and calculation of carbon potential using allometric equations to calculate the total biomass. Spatial analysis using Arc.GIS 10.4 software and the carbon content analysis was carried out using the ashing method. The results showed that the potential carbon stock of Pocut Meurah Intan Forest Park was 640,282 tons. The carbon potential is the carbon stored above the ground in the form of carbon from above-ground biomass (trees, poles, saplings, undergrowth) and organic matter (necromass and litter). The highest carbon potential was found in the secondary dryland forest land cover with a total of 555,204 tons or 167.6 tons ha1 , followed by shrubs of 78,949 tons or 33.3 tons ha -1 , and the lowest potential carbon stock was found in the open field of 303 tons or 2.8 tons ha-1 . The increase in land cover in secondary dryland forests causes increased carbon storage. The low potential for carbon stocks is due to land clearing and a small number of stands, resulting in a decrease in potential carbon stocks.
Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of the vehicle. Classical approaches rely on accurate, complex and difficult-to-derive models of the vehicle and the environment. Reinforcement learning (RL) provides an attractive alternative due to its ability to learn a suitable control policy exclusively from data during a training procedure. However, current methods require several hours to train, have limited success rates and depend on hyperparameters that need to be tuned by trial-and-error. We address all these issues in this work. First, we decompose the landing procedure into a sequence of simpler, but similar learning tasks. This is enabled by applying two instances of the same RL based controller trained for 1D motion for controlling the multi-rotor's movement in both the longitudinal and the lateral directions. Second, we introduce a powerful state space discretization technique that is based on i) kinematic modeling of the moving platform to derive information about the state space topology and ii) structuring the training as a sequential curriculum using transfer learning. Third, we leverage the kinematics model of the moving platform to also derive interpretable hyperparameters for the training process that ensure sufficient maneuverability of the multi-rotor vehicle. The training is performed using the tabular RL method Double Q-Learning. Through extensive simulations we show that the presented method significantly increases the rate of successful landings, while requiring less training time compared to other deep RL approaches. Finally, we deploy and demonstrate our algorithm on real hardware. For all evaluation scenarios we provide statistics on the agent's performance.
Sidi Mohammed Chekouri, Abderrahim Chibi, Mohamed Benbouziane
Abstract The Central Bank of Algeria has announced a managed float of the Algerian dinar since 1994. Yet, there are some substantial differences between various de facto classifications of Algeria’s exchange rate regime. This study looks into the exchange rate regime of Algeria, aiming to identify de facto regime. To identify the implicit basket weights for the Algerian dinar, first the OLS rolling window methodology is used to estimate the celebrated Frankel-Wei regression. Then, the wavelet-based methods are applied to study the co-movement patterns of the exchange rates of the Algerian dinar, US dollar, and Euro. In the main, the OLS rolling window results show that the US dollar and the Euro are the currencies with the most influence over the Algerian dinar. Further, from the Wavelet Multiple Correlation (WMC) results, the US dollar is identified as the potential leader in the implicit basket for the Algerian dinar. Additionally, from the Wavelet Local Multiple Correlation (WLMC) results, it is found that the Algerian DZD, US dollar, and Euro are highly correlated, with a correlation value around 0.90 for most of the time scales. Based on the results obtained, we suggest that Algeria’s exchange rate regime could be a crawling peg and band around the US dollar and Euro.
Economic growth, development, planning, Economics as a science
With the development of industry, drones are appearing in various field. In recent years, deep reinforcement learning has made impressive gains in games, and we are committed to applying deep reinforcement learning algorithms to the field of robotics, moving reinforcement learning algorithms from game scenarios to real-world application scenarios. We are inspired by the LunarLander of OpenAI Gym, we decided to make a bold attempt in the field of reinforcement learning to control drones. At present, there is still a lack of work applying reinforcement learning algorithms to robot control, the physical simulation platform related to robot control is only suitable for the verification of classical algorithms, and is not suitable for accessing reinforcement learning algorithms for the training. In this paper, we will face this problem, bridging the gap between physical simulation platforms and intelligent agent, connecting intelligent agents to a physical simulation platform, allowing agents to learn and complete drone flight tasks in a simulator that approximates the real world. We proposed a reinforcement learning framework based on Gazebo that is a kind of physical simulation platform (ROS-RL), and used three continuous action space reinforcement learning algorithms in the framework to dealing with the problem of autonomous landing of drones. Experiments show the effectiveness of the algorithm, the task of autonomous landing of drones based on reinforcement learning achieved full success.
Land cover classification is a multi-class segmentation task to classify each pixel into a certain natural or man-made category of the earth surface, such as water, soil, natural vegetation, crops, and human infrastructure. Limited by hardware computational resources and memory capacity, most existing studies preprocessed original remote sensing images by down sampling or cropping them into small patches less than 512*512 pixels before sending them to a deep neural network. However, down sampling images incurs spatial detail loss, renders small segments hard to discriminate, and reverses the spatial resolution progress obtained by decades of years of efforts. Cropping images into small patches causes a loss of long-range context information, and restoring the predicted results to their original size brings extra latency. In response to the above weaknesses, we present an efficient lightweight semantic segmentation network termed MKANet. Aimed at the characteristics of top view high-resolution remote sensing imagery, MKANet utilizes sharing kernels to simultaneously and equally handle ground segments of inconsistent scales, and also employs parallel and shallow architecture to boost inference speed and friendly support image patches more than 10X larger. To enhance boundary and small segments discrimination, we also propose a method that captures category impurity areas, exploits boundary information and exerts an extra penalty on boundaries and small segment misjudgment. Both visual interpretations and quantitative metrics of extensive experiments demonstrate that MKANet acquires state-of-the-art accuracy on two land-cover classification datasets and infers 2X faster than other competitive lightweight networks. All these merits highlight the potential of MKANet in practical applications.