Computer Vision-Assisted High-Throughput Screening of Crystallization Additives for Crystal Size, Shape, and Agglomeration Regulation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Additives are widely employed to regulate the morphology, size, and agglomeration degree of crystalline materials during crystallization to enhance their functional, physical, and powder properties. However, the existing methods for screening and validating target additives require a large quantity of materials and involve tedious molecular simulation/crystallization experiments, making them time-consuming, resource-intensive, and reliant on the operator’s experience level. To overcome these challenges, we proposed a computer vision-assisted high-throughput additive screening system (CV-HTPASS) which comprises a high-throughput additive screening device, in situ imaging equipment, and an artificial intelligence (AI)-assisted image-analysis algorithm. Using the CV-HTPASS, we performed high-throughput screening experiments on additives to regulate the succinic acid crystal properties, generating thousands of crystal images with diverse crystal morphologies. To extract valuable crystal information from the massive data and improve the analysis accuracy and efficiency, the AI-based image-analysis algorithm was implemented innovatively for the segmentation, classification, and data mining of crystals with four morphologies to further screen the target additive. Subsequently, scale-up crystallization experiments conducted under optimized conditions demonstrated that succinic acid products exhibited a preferred cubic morphology, reduced agglomeration degree, narrowed crystal size distribution, and improved powder properties. The proposed CV-HTPASS offers a highly efficient approach for scale-up experiments. Further, it provides a platform for the screening of additives and the optimization of the powder properties of crystal products in industrial-scale crystallization processes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it