Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Hamer, Alex; Simms, Daniel M.; Waine, Toby

doi:10.1080/01431161.2020.1864059

Cited by 5 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL has gained many successes in prediction/classification quests. Among all the DL structures, convolutional neural network (CNN) [ 18 , 19 ] is particularly suitable for analyzing 2D/3D images. To help boost the performance of CNN, researches are proposed to modify CNN structures in terms of either depth, or cardinality, or width.…”

Section: Methodsmentioning

confidence: 99%

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

Zhang

et al. 2021

Pattern Recognition Letters

View full text Add to dashboard Cite

Background COVID-19 has caused 3.34m deaths till 13/May/2021. It is now still causing confirmed cases and ongoing deaths every day. Method This study investigated whether fusing chest CT with chest X-ray can help improve the AI's diagnosis performance. Data harmonization is employed to make a homogeneous dataset. We create an end-to-end multiple-input deep convolutional attention network (MIDCAN) by using the convolutional block attention module (CBAM). One input of our model receives 3D chest CT image, and other input receives 2D X-ray image. Besides, multiple-way data augmentation is used to generate fake data on training set. Grad-CAM is used to give explainable heatmap. Results The proposed MIDCAN achieves a sensitivity of 98.10±1.88%, a specificity of 97.95±2.26%, and an accuracy of 98.02±1.35%. Conclusion Our MIDCAN method provides better results than 8 state-of-the-art approaches. We demonstrate the using multiple modalities can achieve better results than individual modality. Also, we demonstrate that CBAM can help improve the diagnosis performance.

show abstract

Section: Methodsmentioning

confidence: 99%

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

Zhang

et al. 2021

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…Recent work has shown the potential to produce accurate and timely agricultural land classification from satellite imagery using convolutional neural networks (CNNs) [6,7]. These deep learning models differ from conventional pixel-and object-based approaches in that they can be trained across multiple years of image data using transfer learning: where a pre-trained model is fine tuned using new labelled image data from a much smaller dataset than was used to train the original model.…”

Section: Introductionmentioning

confidence: 99%

“…Ref. [6] found that transfer learning in Afghanistan's Helmand Province between years required 75% less labelled data than models trained from scratch (no prior training), with improved overall accuracy (>94%).…”

Section: Introductionmentioning

confidence: 99%

Mapping Agricultural Land in Afghanistan’s Opium Provinces Using a Generalised Deep Learning Model and Medium Resolution Satellite Imagery

Simms,

Hamer,

Zeiler

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Understanding the relationship between land use and opium production is critical for monitoring the dynamics of poppy cultivation and developing an effective counter narcotics policy in Afghanistan. However, mapping agricultural land accurately and rapidly is challenging, as current methods require resource-intensive and time consuming manual image-interpretation. Deep convolutional neural nets have been shown to greatly reduce the manual effort in mapping agriculture from satellite imagery but require large amounts of densely labelled training data for model training. Here we develop a generalised model using past images and labels from different medium resolution satellite sensors for fully automatic agricultural land classification using the latest medium resolution satellite imagery. The model (FCN-8) is first trained on Disaster Monitoring Constellation (DMC) satellite images from 2007 to 2009. The effect of shape, texture and spectral features on model performance are investigated along with normalisation in order to standardise input medium resolution imagery from DMC, Landsat-5, Landsat-8, and Sentinel-2 for transfer learning between sensors and across years. Textural features make the highest contribution to overall accuracy (∼73%) while the effect of shape is minimal. The model accuracy on new images, with no additional training, is comparable to visual image interpretation (overall > 95%, user accuracy > 91%, producer accuracy > 85%, and frequency weighted intersection over union > 67%). The model is robust and was used to map agriculture from archive images (1990) and can be used in other areas with similar landscapes. The model can be updated by fine tuning using smaller, sparsely labelled datasets in the future. The generalised model was used to map the change in agricultural area in Helmand Province, showing the expansion of agricultural land into former desert areas. Training generalised deep learning models using data from both new and long-term EO programmes, with little or no requirement for fine tuning, is an exciting opportunity for automating image classification across datasets and through time that can improve our understanding of the environment.

show abstract

“…The moving window integrates time-varying delay information hidden in time series data into the input layer of the CNN. As a result of powerful feature extraction capability, CNN is not only used in image processing [ 16 ], but also in manufacturing industry [ 17 ], which is used to extract the data characteristics of variables in the cement calcination process.…”

Section: Introductionmentioning

confidence: 99%

A Synchronous Prediction Model Based on Multi-Channel CNN with Moving Window for Coal and Electricity Consumption in Cement Calcination Process

Shi

Huang

Hao

et al. 2021

Sensors

View full text Add to dashboard Cite

The precision and reliability of the synchronous prediction of multi energy consumption indicators such as electricity and coal consumption are important for the production optimization of industrial processes (e.g., in the cement industry) due to the deficiency of the coupling relationship of the two indicators while forecasting separately. However, the time lags, coupling, and uncertainties of production variables lead to the difficulty of multi-indicator synchronous prediction. In this paper, a data driven forecast approach combining moving window and multi-channel convolutional neural networks (MWMC-CNN) was proposed to predict electricity and coal consumption synchronously, in which the moving window was designed to extract the time-varying delay feature of the time series data to overcome its impact on energy consumption prediction, and the multi-channel structure was designed to reduce the impact of the redundant parameters between weakly correlated variables of energy prediction. The experimental results implemented by the actual raw data of the cement plant demonstrate that the proposed MWMC-CNN structure has a better performance than without the combination structure of the moving window multi-channel with convolutional neural network.

show abstract

Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Cited by 5 publications

References 37 publications

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

Mapping Agricultural Land in Afghanistan’s Opium Provinces Using a Generalised Deep Learning Model and Medium Resolution Satellite Imagery

A Synchronous Prediction Model Based on Multi-Channel CNN with Moving Window for Coal and Electricity Consumption in Cement Calcination Process

Contact Info

Product

Resources

About