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: 23-00075R2
Evaluation of SMAP and CYGNSS Soil Moistures in Drought Prediction Using Multiple Linear Regression and GLDAS Product
Komi Edokossi, Shuanggen Jin, Andres Calabia, Iñigo Molina, and Usman Mazhar

Drought is a devastating natural hazard and exerts profound effects on both the environment and society. Predicting drought occurrences is significant in aiding decision-making and implementing effective mitigation strategies. In regions characterized by limited data availability, such as Southern Africa, the use of satellite remote sensing data promises an excellent opportunity for achieving this predictive goal. In this study, we assess the effectiveness of Soil Moisture Active Passive (SMAP) and Cyclone Global Navigation Satellite System (CYGNSS) soil moisture data in predicting drought conditions using multiple linear regression–predicted data and Global Land Data Assimilation System (GLDAS) soil moisture data. SMAP and CYGNSS data exhibit strong spatiotemporal congruence with the predicted soil moisture data. Pearson correlation coefficients further underscore this consistency, with correlations of r = 0.78 between GLDAS and SMAP, r = 0.61 between GLDAS and CYGNSS, and r = 0.84 between GLDAS and the estimated soil moisture. The proficient performance of SMAP and CYGNSS soil moisture data in tandem with other variables underscores their efficacy in predicting drought conditions

Manuscript number: 23-00051R2
A Pixel Texture Index Algorithm and its Application
Xiaodan Sun and Xiaofang Sun

Image segmentation is essential for object-oriented analysis, and classification is a critical parameter influencing analysis accuracy. However, image classification and segmentation based on spectral features are easily perturbed by the high-frequency information of a high spatial resolution remotely sensed (HSRRS) image, degrading its classification and segmentation quality. This article first presents a pixel texture index (PTI) by describing the texture and edge in a local area surrounding a pixel. Indeed.. The experimental results highlight that the HSRRS image classification and segmentation quality can be effectively improved by combining it with the PTI image. Indeed, the overall accuracy improved from 7% to 14%, and the kappa can be increased from 11% to 24%, respectively. Five supervised evaluative indicators (i.e., oversegmentation, undersegmentation, edge-matching degree, number of segmentation blocks, and shape error) have reduced from 27.6% to 75%.

Manuscript number: 23-00053R2
Parcel-level Crop Classification in Plain Fragmented Regions Based on Multi-Source Remote Sensing Images
Qiao Zhang, Ziyi Luo, Yang Shen, and Zhoufeng Wang

Accurately obtaining crop cultivation extent and estimating the cultivated area are significant for adjusting regional planting structure. This study proposes a parcel-level crop classification method using time-series, medium-resolution, remote sensing images and single-phase, high-spatial-resolution, remote sensing images. The deep learning semantic segmentation network feature pyramid network with squeeze-and-excitation network (FPN–SENet) and multi-scale segmentation were used to extract cultivated land parcels from Gaofen-2 imagery, while the pixel-level crop types were classified by using support vector machine algorithms from time-series Sentinel-2 images. Then, the parcel-level crop classification was obtained from the pixel-level crop types and land parcels. The proposed method was tested in southwestern China to extract main winter–spring crops and achieved a good performance. Specifically, the FPN-SENet model outperformed other models in cultivated land extraction, with an F1 of 0.872. The crop classification overall accuracy is 0.910 and the kappa coefficient is 0.861. This study provides a technical reference for monitoring cultivated land and can be applied in other regions.

Manuscript number: 23-00078R2
Debris Flow Susceptibility Evaluation Based on Multi-level Feature Extraction CNN Model: A Case Study of Nujiang Prefecture, China
Xu Wang, Baoyun Wang, Ruohao Yuan, Yumeng Luo, and Cunxi Liu

Debris flow susceptibility evaluation plays a crucial role in the prevention and control of debris flow disasters. Therefore, this paper proposes a convolutional neural network model named multi-level feature extraction network (MFENet). First, a dual-channel CNN architecture incorporating the Embedding Channel Attention mechanism is used to extract shallow features from both digital elevation model images and multispectral images. Subsequently, channel shuffle and feature concatenation are applied to the features from the two channels to obtain fused feature sets. Following this, a deep feature extraction is performed on the fused feature sets using a residual module improved by maximum pooling. Finally, the susceptibility index of gullies to debris flows is calculated based on the similarity scores. Experimental results demonstrate that the model exhibits favorable classification performance, with an accuracy of 73.45%. Furthermore, the percentage of debris flow valleys in high and very high susceptibility zones reaches 93.97%.

Manuscript number: 22-00132R3
Land Use Change in the Yangtze River Economic Belt during 2010 to 2020 and Future Comprehensive Prediction Based on Markov and ARIMA Models
Haotian Zheng, Fan Yu, Huawei Wan, Peirong Shi, and Haonan Wang

The key data for accurate prediction is of great significance to accurately carry out the next step of sustainable land use development plan according to the demand of China. Conse-quently, the main purposes of our study are : (1) to delineate the characteristics of land use transitions within the Yangtze River Economic Belt; (2) to use the Markov model and the autoregressive integrated moving average (ARIMA) model for comparative analysis and prediction of land use distribution. This study analyzes land use/cover change (LUCC) data from 2010 and 2020 using the land use transition matrix, dynamic degree, and compre-hensive index model and predicts 2025 land use by the Markov model.. The study identifies a reduction in land usage over 11 years, particularly in grassland. The Markov and ARIMA models’ significance is 0.002 (P < 0.01) , showing arable land and woodland dominance, with varying changes in other land types.

Manuscript number: 23-00074R2
An Improved YOLO Network for Insulator and Insulator Defect Detection in UAV Images
Fangrong Zhou, Lifeng Liu, Hao Hu, Weishi Jin, Zezhong Zheng, Zhongnian Li, Yi Ma, and Qun Wang

The power grid plays a vital role in the construction of livelihood projects by transmitting electrical energy. In the event of insulator explosions on power grid towers, these insulators may detach, presenting potential safety risks to transmission lines. The identification of such failures relies on the examination of images captured by unmanned aerial vehicles (UAVs). However, accurately detecting insulator defects remains challenging, particularly when dealing with variations in size. Existing methods exhibit limited accuracy in detecting small objects. In this paper, we propose a novel detection method that incorporates the convolutional block attention module (CBAM) as an attention mechanism into the backbone of the “you only look once” version 5 (YOLOv5) model. Additionally, we integrate a residual structure into the model to learn additional information and features related to insulators, thereby enhancing detection efficiency. Experimental results demonstrate that our proposed method achieved F1 scores of 0.87 for insulator detection and 0.89 for insulator defect detection. The improved YOLOv5 network shows promise in detecting insulators and their defects in UAV images.

Manuscript number: 23-00083R2
Real-Time Semantic Segmentation of Remote Sensing Images for Land Management
Yinsheng Zhang, Ru Ji, Yuxiang Hu, Yulong Yang, Xin Chen, Xiuxian Duan, and Huilin Shan

Remote sensing image segmentation is a crucial technique in the field of land management. However, existing semantic segmentation networks require a large number of floating-point operations (FLOPs) and have long run times. In this paper, we propose a dual-path feature aggregation network (DPFANet) specifically designed for the low-latency operations required in land management applications. Firstly, we use four sets of spatially separable convolutions with varying dilation rates to extract spatial features. Additionally, we use an improved version of MobileNetV2 to extract semantic features. Furthermore, we use an asymmetric multi-scale fusion module and dual-path feature aggregation module to enhance feature extraction and fusion. Finally, a decoder is constructed to enable progressive up-sampling. Experimental results on the Potsdam data set and the Gaofen image data set (GID) demonstrate that DPFANet achieves overall accuracy of 92.2% and 89.3%, respectively. The FLOPs are 6.72 giga and the number of parameters is 2.067 million.

Manuscript number: 24-00001R2
Monitoring an Ecosystem in Crisis: Measuring Seagrass Meadow Loss Using Deep Learning in Mosquito Lagoon, Florida
Stephanie A. Insalaco, Hannah V. Herrero, Russ Limber, Clancy Oliver, and William B. Wolfson

The ecosystem of Mosquito Lagoon, Florida, has been rapidly deteriorating since the 2010s, with a notable decline in keystone seagrass species. Seagrass is vital for many species in the lagoon, but nutrient overloading, algal blooms, boating, manatee grazing, and other factors have led to its loss. To understand this decline, a deep neural network analyzed Landsat imagery from 2000 to 2020. Results showed significant seagrass loss post-2013, coinciding with the 2011–2013 super algal bloom. Seagrass abundance varied annually, with the model performing best in years with higher seagrass coverage. While the deep learning method successfully identified seagrass, it also revealed that recent seagrass coverage is almost non-existent. This monitoring approach could aid in ecosystem recovery if coupled with appropriate policies for Mosquito Lagoon’s restoration.