As a convenience to ASPRS members, in-press peer reviewed articles approved for publication in forthcoming issues of PE&RS are listed below.

Manuscript number: 24-00065R2
Remote sensing tailing pond image detection method based on YOLOv8-RVSW
ZhengJun Dang and Kun Li

This study proposes an automated tailings pond-detection method based on the YOLOv8-RVSW model to address the limitations of traditional surveys. A tailings pond dataset was created using high-resolution satellite images, and data quality was improved through data augmentation techniques. In the model, YOLOv8’s backbone feature network was replaced with RepViT to effectively capture global and local information. Additionally, the C2f module was enhanced to QuadraSE_C2f to focus on essential feature channels, and WIoUv3 was used as the loss function to improve object localization and detection accuracy. Experimental results indicate that compared with the original model, accuracy increased by 3.9% to 97.4%, recall improved by 4.9% to 96.3%, and mean average precision rose by 2.4% to 98.5%. This method significantly enhances the automation and intelligence of tailings pond monitoring, providing an effective tool for emergency monitoring.

Manuscript number: 24-00027R3
Monitoring LULC Changes in Babil Province for Sustainable Development Purposes Within the Period 2004–2023
Hayder Hameed Jassoom and Rabab Saadoon Abdoon

Land use and land cover studies are fundamental to achieving sustainable development goals by providing the information necessary for informed decision-making in social and economic development and natural resource management. This study relied on remote sensing data to analyze and assess land use and land cover changes in Babil Province, Iraq, over the past two decades. The study focused on identifying the patterns and factors influencing these changes, using Landsat satellite imagery to create digital maps classifying land into four main categories: urban lands, bare soil lands, water bodies, and vegetation lands. The results showed a noticeable expansion of urban lands at the expense of bare soil lands, primarily attributed to population growth, economic development, and improved security conditions. This study underscores the importance of sustainable land management and urban planning in Babil Province. These results highlight the importance of sustainable land management in Babil Province, including sound urban planning considering urban expansion’s environmental, social, and economic effects. The classification was implemented using a maximum likelihood classifier, and the accuracy assessment yielded satisfactory results with an overall accuracy of 93.5517%. This study encourages using artificial intelligence to track and analyze land use changes in Babil.

Manuscript number: 24-00041R2
Landslide Evolution Assessment Based on Sequential InSAR Methods in the Kunming Transmission Line Corridor
Gang Wen, Yizuo Li, Chuhang Xie, Zezhong Zheng, Yi Ma, Fangrong Zhou, Baiyan Su, and Huahui Tang

The security of the transmission line corridor is an important guarantee for the sustainable supply of electricity and an important prerequisite for the rapid development of the economy. Transmission corridors located in high mountains and valleys are often threatened by geological disasters, which seriously affect their stable operation. This research investigates the landslide in the Kunming transmission corridor using 79 Sentinel-1A SAR images from July 2020 to October 2021. Using interferometric synthetic aperture radar (InSAR) methods, deformation changes before the landslide are analyzed. Factors like precipitation, lithology, and vegetation coverage demonstrate a correlation with landslide occurrence. Seasonal variations in deformation were related to precipitation. The landslide’s primary causes are attributed to precipitation, carbonate karstification, and vegetation coverage. Ultimately, this research establishes a correlation between deformation changes and influencing factors in the Kunming transmission corridor, contributing to a deeper understanding of landslide evolution and ensuring the corridor’s security for sustainable electricity supply and economic development.

Manuscript number: 24-00036R1
Adaptive Orientation Object-Detection Method for Large-scale Remote Sensing Images Based on Multi-scale Block Fusion
Yanli Wang, Zhipeng Dong, Mi Wang, and Yi Ding

Object detection is crucial to extracting and analyzing information autonomously from high-resolution remote sensing images (HRSIs). To address ideal blocking for large-scale HRSI object detection, this study uses a novel adaptive orientation object-detection method for large-scale HRSIs based on multi-scale block fusion. An adaptive orientation object-detection framework based on a convolutional neural network is applied to detect diverse objects of large-scale HRSIs through different block scales; average precision (AP) values of diverse object-detection results are calculated at different block scales. Then, block scales matching the largest AP values of diverse objects are determined based on statistical results of the AP values of the diverse object at different block scales. Finally, object-detection results at block scales matching the largest AP values of diverse objects are fused by the non-maximum suppression algorithm to achieve large-scale HRSI object-detection results. Experimental findings reveal that the proposed method is better than any single block-scale object-detection method, resulting in satisfactory large-scale HRSI object-detection results.

Manuscript number: 24-00035R2
Spatiotemporal Behavior of Active Forest Fires Using Time-Series MODIS C6 Data
Syed Azimuddin and R.S. Dwivedi

Forest fires have a profound influence on the economy, ecology, and environment. Realizing the potential of remote sensing in forest fire management, a study was taken up to investigate the spatiotemporal behavior of active forest fires in a mountainous terrain of Uttarakhand State, north India, using 15 years’ time-series historical MODIS (C6) active fire point products. Results indicate an overall fire incidence detection accuracy of 62.3% with a KHAT value of 0.59. Moreover, a regular trend in intra-annual behavior in fire incidences with peaks during the hot and dry period of the year was observed and a large year-to-year variability in fire regimes with no significant trends over time could be noticed. The approach and results are discussed in detail along with the future perspective.

Manuscript number: 24-00072R3
Artificial Neural Network Multi-layer Perceptron Models to Classify California’s Crops using Harmonized Landsat Sentinel (HLS) Data
Richard McCormick, Prasad S. Thenkabail, Itiya Aneece, Pardhasaradhi Teluguntla, Adam J. Oliphant, and Daniel Foley

Advances in remote sensing and machine learning are enhancing cropland classification, vital for global food and water security. We used multispectral Harmonized Landsat 8 Sentinel-2 (HLS) 30-m data in an artificial neural network (ANN) multi-layer perceptron (MLP) model to classify five crop classes (cotton, alfalfa, tree crops, grapes, and others) in California’s Central Valley. The ANN MLP model, trained on 2021 data from the United States Department of Agriculture’s Cropland Data Layer, was validated by classifying crops for an independent year 2022. Across the five crop classes, the overall accuracy was 74%. Producer’s and user’s accuracies ranged from 65% to 87%, with cotton achieving the highest accuracies. The study highlights the potential of using deep learning with HLS time series data for accurate global crop classification.

Manuscript number: 24-00060R2
RSODNet: Lightweight Remote Sensing Image Object Detection Combined with BCDNS Compression Algorithm
Xinyu Zhu, Zhihua Zhang, Wei Wang, Yuhao Hou, and Shuwen Yang

In recent years, with the gradual increase of neural network Params (the aggregate of trainable elements in a model, including weights, biases, and other adjustable elements) and calculation volume, model compression within an acceptable range of network accuracy variations has emerged as a prominent research focus in the field of deep learning. Model pruning and knowledge distillation have been widely used for reducing the complexity and storage cost of neural networks. This study designs the Remote Sensing Object Detection Network (RSODNet), a lightweight model for remote sensing image object detection, and proposes bridging cross-task distillation network slimming (BCDNS) as a method that integrates model pruning and knowledge distillation. The experiment results indicate that RSODNet outperforms the YOLOv8 model in various metrics while maintaining almost unchanged Params and calculation volume. The BCDNS method eliminates redundant channels while preserving a priori knowledge of the initial model intact. This study offers technical support for compressed models used in object detection from remote sensing images.