[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
Remote Sensing Technology for Agricultural and Land Management
sensors-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Remote Sensing Technology for Agricultural and Land Management

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Environmental Sensing".

Deadline for manuscript submissions: 25 May 2025 | Viewed by 4283

Special Issue Editor

Prof. Dr. Paul Krause

E-Mail Website
Guest Editor
Computer Science Research Centre, University of Surrey, Guildford GU2 7XH, UK
Interests: machine learning; good old fashioned AI; ecological modelling; medical AI; AI and environmental modelling/monitoring
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With climate change and biodiversity crises, we need to rethink the way we perform agriculture and land management. Working with nature rather than trying to control it has the potential to increase carbon capture and biodiversity in agricultural units without sacrificing productivity. With regard to the management of the wider landscape, practices in “rewilding” are showing their potential to enhance the ecosystem services such as flood control, water quality, pollination, and amenity that wild spaces provide.

We are still learning how to manage this change effectively. Continuous assessment of land holdings is needed in order to ensure that the management goals are being met. This can only be achieved cost-effectively at scale through the use of remote sensing. This Special Issue will focus on techniques and case studies that build an experience base for the use of remote sensing to manage agricultural units and natural spaces in an environmentally positive and sustainable way.

Submissions of research papers, case studies, and review articles are welcome.

Prof. Dr. Paul Krause
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sensor networks
  • Internet of Things
  • environmental monitoring
  • satellite image analysis
  • ecological intensification
  • conservation agriculture
  • ecosystem services
  • biodiversity assessment

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

26 pages, 17954 KiB  
Article
A Large-Scale Agricultural Land Classification Method Based on Synergistic Integration of Time Series Red-Edge Vegetation Index and Phenological Features
by Huansan Zhao, Chunyan Chang, Zhuoran Wang and Gengxing Zhao
Sensors 2025, 25(2), 503; https://doi.org/10.3390/s25020503 - 16 Jan 2025
Viewed by 656
Abstract
Agricultural land classification plays a pivotal role in food security and ecological sustainability, yet achieving accurate large-scale mapping remains challenging. This study presents methodological innovations through a multi-level feature enhancement framework that transcends traditional time series analysis. Using Shandong Province, northern China’s agricultural [...] Read more.
Agricultural land classification plays a pivotal role in food security and ecological sustainability, yet achieving accurate large-scale mapping remains challenging. This study presents methodological innovations through a multi-level feature enhancement framework that transcends traditional time series analysis. Using Shandong Province, northern China’s agricultural heartland, as a case study, we first established a foundation with time series red-edge vegetation indices (REVI) from Sentinel-2 imagery, uniquely combining the normalized difference red edge index (NDRE705) and plant senescence reflectance index (PSRI). Moving beyond conventional time series analysis, we innovatively amplified key temporal characteristics through newly designed spatial feature parameters (SFPs) and phenological feature parameters (PFPs). This strategic enhancement of critical temporal points significantly improved classification performance by capturing subtle spatial patterns and phenological transitions that are often overlooked in traditional approaches. The study yielded three significant findings: (1) The synergistic application of NDRE705 and PSRI significantly outperformed single-index approaches, demonstrating the effectiveness of our dual-index strategy; (2) The integration of SFPs and PFPs with time series REVI markedly enhanced feature discrimination at crucial growth stages, with PFPs showing superior capability in distinguishing agricultural land types through amplified phenological signatures; (3) Our optimal classification scheme (FC6), leveraging both enhanced spatial and phenological features, achieved remarkable accuracy (93.21%) with a Kappa coefficient of 0.9159, representing improvements of 4.83% and 0.0538, respectively, over the baseline approach. This comprehensive framework successfully mapped 120,996 km2 of agricultural land, differentiating winter wheat–summer maize rotation areas (39.44%), single-season crop fields (36.16%), orchards (14.49%), and facility vegetable fields (9.91%). Our approach advances the field by introducing a robust, scalable methodology that not only utilizes the full potential of time series data but also strategically enhances critical temporal features for improved classification accuracy, particularly valuable for regions with complex farming systems and diverse crop patterns. Full article
(This article belongs to the Special Issue Remote Sensing Technology for Agricultural and Land Management)
►▼ Show Figures

Figure 1

Figure 1
<p>Overview of the study area. (The base map data is ESA/world_cover_2020, and the lower left corner displays the DEM of Shandong Province).</p> Full article ">Figure 2
<p>Technical route of the research.</p> Full article ">Figure 3
<p>Phenological information of major agricultural lands in Shandong Province (crop calendar). (Summarization based on statistical information from the Department of Agriculture and Rural Affairs of Shandong Province [<a href="#B49-sensors-25-00503" class="html-bibr">49</a>]). The color changes represent the process of crop growth to decay.</p> Full article ">Figure 4
<p>Schematic diagram of the initial sampling point deployment.</p> Full article ">Figure 5
<p>Classification sample distribution.</p> Full article ">Figure 6
<p>Visualization of NDRE<sub>705</sub> and PSRI time series curves of different agricultural land types in Shandong Province.</p> Full article ">Figure 7
<p>Accuracy of agricultural land classification for different original time series classification schemes.</p> Full article ">Figure 8
<p>Feature importance of SFPs. (It shows the feature importance of the three SFPs in each time phase).</p> Full article ">Figure 9
<p>The 12 PFPs with the highest contribution. (Arranged in descending order of importance).</p> Full article ">Figure 10
<p>Details of the classification of different types of agricultural land. (<b>a1</b>,<b>a2</b>) Winter wheat–summer maize rotation area; (<b>b1</b>,<b>b2</b>) Orchard; (<b>c1</b>,<b>c2</b>) Single-season crop field; (<b>d1</b>,<b>d2</b>) Facility vegetable field. Note: Imagery is a high-resolution Google Earth image from October 2019.</p> Full article ">Figure 11
<p>Distribution of agricultural land types in Shandong Province.</p> Full article ">
29 pages, 13171 KiB  
Article
Enhancing Coffee Agroforestry Systems Suitability Using Geospatial Analysis and Sentinel Satellite Data in Gedeo Zone, Ethiopia
by Wondifraw Nigussie, Husam Al-Najjar, Wanchang Zhang, Eshetu Yirsaw, Worku Nega, Zhijie Zhang and Bahareh Kalantar
Sensors 2024, 24(19), 6287; https://doi.org/10.3390/s24196287 - 28 Sep 2024
Cited by 1 | Viewed by 1529
Abstract
The Gedeo zone agroforestry systems are the main source of Ethiopia’s coffee beans. However, land-use and suitability analyses are not well documented due to complex topography, heterogeneous agroforestry, and lack of information. This research aimed to map the coffee coverage and identify land [...] Read more.
The Gedeo zone agroforestry systems are the main source of Ethiopia’s coffee beans. However, land-use and suitability analyses are not well documented due to complex topography, heterogeneous agroforestry, and lack of information. This research aimed to map the coffee coverage and identify land suitability for coffee plantations using remote sensing, Geographic Information Systems (GIS), and the Analytical Hierarchy Process (AHP) in the Gedeo zone, Southern Ethiopia. Remote sensing classifiers often confuse agroforestry and plantations like coffee cover with forest cover because of their similar spectral signatures. Mapping shaded coffee in Gedeo agroforestry using optical or multispectral remote sensing is challenging. To address this, the study identified and mapped coffee coverage from Sentinel-1 data with a decibel (dB) value matched to actual coffee coverage. The actual field data were overlaid on Sentinel-1, which was used to extract the raster value. Pre-processing, classification, standardization, and reclassification of thematic layers were performed to find potential areas for coffee plantation. Hierarchy levels of the main criteria were formed based on climatological, edaphological, physiographic, and socioeconomic factors. These criteria were divided into 14 sub-criteria, reclassified based on their impact on coffee growing, with their relative weights derived using AHP. From the total study area of 1356.2 km2, the mapped coffee coverage is 583 km2. The outcome of the final computed factor weight indicated that average annual temperature and mean annual rainfall are the primary factors, followed by annual mean maximum temperature, elevation, annual mean minimum temperature, soil pH, Land Use/Land Cover (LULC), soil texture, Cation Exchange Capacity (CEC), slope, Soil Organic Matter (SOM), aspect, distance to roads, and distance to water, respectively. The identified coffee plantation potential land suitability reveals unsuitable (413 km2), sub-suitable (596.1 km2), and suitable (347.1 km2) areas. This study provides comprehensive spatial details for Ethiopian cultivators, government officials, and agricultural extension specialists to select optimal coffee farming locations, enhancing food security and economic prosperity. Full article
(This article belongs to the Special Issue Remote Sensing Technology for Agricultural and Land Management)
►▼ Show Figures

Figure 1

Figure 1
<p>Location of the study area.</p> Full article ">Figure 2
<p>Methodological flowchart of the research.</p> Full article ">Figure 3
<p>Pre-processed images (<b>a</b>) sentinel-1 (SAR), and (<b>b</b>) sentinel-2 (MSI).</p> Full article ">Figure 4
<p>Agro-ecological classification, (<b>a</b>) sample field data of coffee coverage, and (<b>b</b>) processed sentinel-1.</p> Full article ">Figure 5
<p>Maps of physiographic thematic layers (<b>a</b>) Elevation, (<b>b</b>) Slope, (<b>c</b>) Aspect, (<b>d</b>) Reclassified elevation, (<b>e</b>) Reclassified slope, (<b>f</b>) Reclassified aspect.</p> Full article ">Figure 6
<p>Maps of edaphological thematic layers. (<b>a</b>) Soil texture, (<b>b</b>) Reclassified soil texture, (<b>c</b>) Soil organic matter, (<b>d</b>) Reclassified soil organic matter, (<b>e</b>) Soil pH, (<b>f</b>) Reclassified soil pH, (<b>g</b>) CEC, (<b>h</b>) Reclassified CEC.</p> Full article ">Figure 7
<p>Maps of climatological thematic layers, (<b>a</b>) Mean annual rainfall, (<b>b</b>) Reclassified mean annual rainfall, (<b>c</b>) Annual mean maximum temperature, (<b>d</b>) Reclassified maximum temperature, (<b>e</b>) Average annual temperature, (<b>f</b>) Reclassified average annual temperature, (<b>g</b>) Annual mean minimum temperature, (<b>h</b>) Reclassified mean minimum temperature.</p> Full article ">Figure 8
<p>Maps of socioeconomic thematic layers, (<b>a</b>) LULC in 2021, (<b>b</b>) Distance to road network, (<b>c</b>) Distance to river network, (<b>d</b>) Reclassified LULC, (<b>e</b>) Reclassified distance to road, (<b>f</b>) Reclassified distance to river.</p> Full article ">Figure 9
<p>Current potential coffee coverage areas in Gedeo zone.</p> Full article ">Figure 10
<p>Identified potential areas for coffee plantation.</p> Full article ">Figure 11
<p>Area coverage of identified potential coffee plantation.</p> Full article ">
28 pages, 16525 KiB  
Article
DMAF-NET: Deep Multi-Scale Attention Fusion Network for Hyperspectral Image Classification with Limited Samples
by Hufeng Guo and Wenyi Liu
Sensors 2024, 24(10), 3153; https://doi.org/10.3390/s24103153 - 15 May 2024
Cited by 1 | Viewed by 1453
Abstract
In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the [...] Read more.
In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the HSIC task, such as the lack of labeled training samples, which constrains the classification accuracy and generalization ability of CNNs. To address this problem, a deep multi-scale attention fusion network (DMAF-NET) is proposed in this paper. This network is based on multi-scale features and fully exploits the deep features of samples from multiple levels and different perspectives with an aim to enhance HSIC results using limited samples. The innovation of this article is mainly reflected in three aspects: Firstly, a novel baseline network for multi-scale feature extraction is designed with a pyramid structure and densely connected 3D octave convolutional network enabling the extraction of deep-level information from features at different granularities. Secondly, a multi-scale spatial–spectral attention module and a pyramidal multi-scale channel attention module are designed, respectively. This allows modeling of the comprehensive dependencies of coordinates and directions, local and global, in four dimensions. Finally, a multi-attention fusion module is designed to effectively combine feature mappings extracted from multiple branches. Extensive experiments on four popular datasets demonstrate that the proposed method can achieve high classification accuracy even with fewer labeled samples. Full article
(This article belongs to the Special Issue Remote Sensing Technology for Agricultural and Land Management)
►▼ Show Figures

Figure 1

Figure 1
<p>Architecture of the proposed DMAF-NET.</p> Full article ">Figure 2
<p>Multi-scale feature extraction backbone network.</p> Full article ">Figure 3
<p>Three-dimensional multi-scale space–spectral attention enhancement module.</p> Full article ">Figure 4
<p>Four-dimensional pyramid-style multi-scale channel attention module.</p> Full article ">Figure 5
<p>Multi-attention feature fusion module.</p> Full article ">Figure 6
<p>The pseudo-color images and the corresponding ground truth maps for the SA, UP, and IP datasets. (<b>a-1</b>) Pseudo-color map of SA. (<b>a-2</b>) Ground truth map of SA. (<b>b-1</b>) Pseudo-color map of UP. (<b>b-2</b>) Ground truth map of UP. (<b>c-1</b>) Pseudo-color map of IP. (<b>c-2</b>) Ground truth map of IP. (<b>d-1</b>) Pseudo-color map of LK. (<b>d-2</b>) Ground truth map of LK.</p> Full article ">Figure 7
<p>Classification results (%) and training time (seconds) for each dataset under different patch sizes.</p> Full article ">Figure 8
<p>Classification results (%) and training time (seconds) for each dataset with a different number of components retained during PCA operation.</p> Full article ">Figure 9
<p>Classification maps generated by all of the competing methods on the SA dataset with 10 training samples for each category. (<b>a</b>) 3D-CNN. (<b>b</b>) HybridSN. (<b>c</b>) SSRN. (<b>d</b>) Tri-CNN. (<b>e</b>) MCNN-CP. (<b>f</b>) SSFTT. (<b>g</b>) Oct-MCNN-HS. (<b>h</b>) Proposed method.</p> Full article ">Figure 10
<p>Classification maps generated by all of the competing methods on the UP dataset with 10 training samples for each category. (<b>a</b>) 3D-CNN. (<b>b</b>) HybridSN. (<b>c</b>) SSRN. (<b>d</b>) Tri-CNN. (<b>e</b>) MCNN-CP. (<b>f</b>) SSFTT. (<b>g</b>) Oct-MCNN-HS. (<b>h</b>) Proposed method.</p> Full article ">Figure 11
<p>Classification maps generated by all of the competing methods on the IP dataset with 10 training samples for each category. (<b>a</b>) 3D-CNN. (<b>b</b>) HybridSN. (<b>c</b>) SSRN. (<b>d</b>) Tri-CNN. (<b>e</b>) MCNN-CP. (<b>f</b>) SSFTT. (<b>g</b>) Oct-MCNN-HS. (<b>h</b>) Proposed method.</p> Full article ">Figure 12
<p>Classification maps generated by all of the competing methods on the LK dataset with 10 training samples for each category. (<b>a</b>) 3D-CNN. (<b>b</b>) HybridSN. (<b>c</b>) SSRN. (<b>d</b>) Tri-CNN. (<b>e</b>) MCNN-CP. (<b>f</b>) SSFTT. (<b>g</b>) Oct-MCNN-HS. (<b>h</b>) Proposed method.</p> Full article ">Figure 13
<p>Classification results (%) for all competing methods using different amount of training samples on the three datasets; fixed quantity sampling is used for each category. (<b>a-1</b>) The OA of SA dataset. (<b>a-2</b>) The AA of SA dataset. (<b>a-3</b>) The Kappa of SA dataset. (<b>b-1</b>) The OA of UP dataset. (<b>b-2</b>) The AA of UP dataset. (<b>b-3</b>) The Kappa of UP dataset. (<b>c-1</b>) The OA of IP dataset. (<b>c-2</b>) The AA of IP dataset. (<b>c-3</b>) The Kappa of IP dataset. (<b>d-1</b>) The OA of LK dataset. (<b>d-2</b>) The AA of LK dataset. (<b>d-3</b>) The Kappa of LK dataset.</p> Full article ">Figure 14
<p>Classification results (%) for all competing methods using different amount of training samples on the three datasets; fixed proportion sampling is used for each category. (<b>a-1</b>) The OA of SA dataset. (<b>a-2</b>) The AA of SA dataset. (<b>a-3</b>) The Kappa of SA dataset. (<b>b-1</b>) The OA of UP dataset. (<b>b-2</b>) The AA of UP dataset. (<b>b-3</b>) The Kappa of UP dataset. (<b>c-1</b>) The OA of IP dataset. (<b>c-2</b>) The AA of IP dataset. (<b>c-3</b>) The Kappa of IP dataset. (<b>d-1</b>) The OA of LK dataset. (<b>d-2</b>) The AA of LK dataset. (<b>d-3</b>) The Kappa of LK dataset.</p> Full article ">Figure 15
<p>Classification results (%) of ablation experiments.</p> Full article ">Figure 16
<p>The influence of different size convolutional kernels in three branches of baseline.</p> Full article ">Figure 17
<p>The influence of varying numbers of 3D octave convolutions in three branches of baseline.</p> Full article ">Figure 18
<p>Classification results (%) of different dimensionality reduction method.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop