Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
宮崎 加奈子*; 笛田 和希*; 門脇 正尚; 寺田 宏明; 香西 直文; 岩田 孟; 堀江 憲路*; 竹原 真美*; 山崎 信哉*; Grambow, B.*; et al.
Journal of Hazardous Materials, 511, p.142180_1 - 142180_17, 2026/06
被引用回数:0 パーセンタイル:0.00(Engineering, Environmental)Radioactive cesium-rich microparticles (CsMPs) released from the Fukushima Daiichi Nuclear Power Plant (FDNPP) in 2011 pose a persistent environmental concern, yet their initial atmospheric dispersion has remained poorly constrained. To elucidate their release dynamics, we quantified CsMPs in 100 surface soil samples collected across Fukushima Prefecture in July 2011. CsMP abundance and radioactive fraction (RF) ranged from 0 to 52,300 particles kg
; (dry weight) and 0-61.85% of deposited
Cs, respectively. Integrating these results with WSPEEDI atmospheric simulations reveals a major formation event of CsMPs around 03:00 JST on 15th March 2011. The plume emitted at this time was heavily enriched in CsMPs, whereas plumes released after 00:00 JST on 16th March 2011 contained no detectable CsMPs, indicating that particle formation had ceased by then. The widespread distribution of CsMPs across Fukushima Prefecture is therefore attributed primarily to this single plume on 15th March 2011. Directional differences in CsMP abundance reflect temporal variations in CsMP density within the plume, with maximum estimated concentrations of 2,070 particles m
; toward the southwest and 4,700 particles m
; toward the northwest. Additionally, elevated CsMP densities coupled with relatively low RF in the northwest suggest supplementary deposition of water-soluble cesium between 17:00 and 23:00 JST on 15 March. These findings constrain the timing and mechanisms of CsMP formation and dispersion, providing essential insights for environmental reconstruction and future radiological risk assessment.
萩原 大樹; 小菅 淳; 斉藤 淳一; 浪江 将成; 木曽原 直之; 峰原 英介*; 坪井 昭彦; 石森 有
Next Research (Internet), 8, p.101581_1 - 101581_9, 2026/06
To understand how Type-A Cs-bearing microparticles were generated at the Fukushima Daiichi nuclear power plant, identifying the materials from which these particles originated is important. In this study, we focus on a methodological approach for generating Cs-bearing microparticles by laser irradiation of glass-fibers-based filter materials, with the aim of producing surrogate particles under controlled laboratory conditions. To evaluate this approach, a series of experiments was conducted, including vapor-phase exposure and aqueous loading of Cs, Fe, and Zn onto filter substrates, followed by laser irradiation to induce rapid, localized high-temperature effects. Morphology and size distributions of the Cs-containing surrogate particles were found to be comparable to those reported for Type-A particles, within the scope of the applied analytical methods. Overall, a reproducible laboratory framework was established for producing Cs-bearing surrogate microparticles suitable for systematic characterization, while not aiming to fully reproduce specific accident conditions.
福田 航大; 小原 徹*
Nuclear Technology, 212(6), p.1567 - 1578, 2026/06
被引用回数:0 パーセンタイル:0.00(Nuclear Science & Technology)Offshore floating nuclear power plants (OFNPs) are gaining attention as safe and location-flexible means for nuclear energy utilization. Although platform motion in the marine environment may affect reactor kinetics, particularly in boiling water reactors (BWRs), BWR-type OFNPs are expected to have high economic efficiency. This study investigated the reactor power behavior of a BWR-type OFNP using three-dimensional transient neutronics-thermal hydraulics coupled analysis. Heave and pitch motions were considered under realistic wave conditions using a typical BWR model. The results show that the reactor power and its distribution can vary because of the wave-induced platform motion; however, the amplitude of these variations is sufficiently small to ensure normal operation, even under the extreme wave conditions of a one-in-10,000-year storm. Although the results of the present study demonstrate the ability of BWR-type OFNPs to provide a safe and stable energy supply, they also suggest the need for further research. Further studies are needed to address the complex wave conditions and assess the effects of the platform motion on ancillary systems, such as recirculation systems.
中村 勇気*; 小島 良洋*; 山下 拓哉; 下村 健太; 溝上 伸也
Journal of Nuclear Science and Technology, 62(12), p.1226 - 1230, 2025/12
被引用回数:0 パーセンタイル:0.00(Nuclear Science & Technology)In 2011, at the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident, it has been reported that several Units of containment vessel had failed, and large quantity of radionuclides had been released into the environment, however, the detail of accident progression with core melt, reactor and containment vessel failure, has still large uncertainties. Especially for the Unit 2 and Unit 3, even they had succeeded in the initial core cooling, at last lost cooling system and fell into severe accident into large release of the fission product into the environment. To clarify these uncertainties in accident scenario, considering the latest information and several insights, the latest accident scenario for Unit 2 and Unit 3 are studied using the severe accident analysis code in this study. It is shown that both Units would result in the thermal stratification in the containment water which encouraged the containment pressure increase at the early phase of the accident. On the other hand, it would be also possible that containment leakage happened to decrease the containment pressure at the later phase of the accident.
池之上 翼; 谷 享*; 川村 英之; 佐藤 雄飛*
Environmental Science & Technology, 59(38), p.20588 - 20594, 2025/09
被引用回数:3 パーセンタイル:66.63(Engineering, Environmental)2023年以降、福島第一原子力発電所(1F)事故由来のトリチウムを含むALPS処理水が海洋放出されている。福島沿岸で採取された海産物のモニタリングの結果はトリチウム濃度の増加はごくわずかであることが示した。しかし、このモニタリングには、データ公開の遅れやサンプル数の制限といった制約がある。したがって、海産物に高濃度のトリチウムが蓄積する可能性を正確に評価するためには、予測による推定が必要である。本研究では、数値シミュレーションを用いて福島沿岸におけるヒラメ中トリチウム濃度を推定した。この推定では、トリチウム水(HTO)の海洋拡散モデルと海洋生物へのトリチウム移行モデルを組み合わせた。ヒラメへのトリチウムの蓄積は、生物中に長期間留まるトリチウムの化学形態である有機結合型トリチウム(OBT)として評価された。まず、海洋拡散モデルの再現性を福島沿岸の実測データを用いて検証し、計算結果と実測データとがよく一致することを確認した。次に、1Fからのトリチウム放出量を仮想的に最大と設定した場合のヒラメ中OBT濃度を推定した。その結果、1Fから100km以内の距離の場所であっても、OBTの最大濃度は環境水中のトリチウムの自然レベルと同程度であることが示された。また、本研究で推定されたヒラメ中OBT濃度の最大値に基づくと、ヒラメの摂取による内部被ばく量は無視できるレベルであった。
月森 和之; 矢田 浩基
Journal of Pressure Vessel Technology, 147(3), p.031901_1 - 031901_9, 2025/06
被引用回数:0 パーセンタイル:0.00(Engineering, Mechanical)日本では、福島第一原子力発電所の事故以来、原子力プラントに対して厳しい安全対策が取られている。シビアアクシデント時において、放射性物質を内包する危機がそのバウンダリ機能を維持できるか否かが重要な関心事となる。本研究では、高速炉の1時冷却材を内包する容器等のバウンダリを構成する構造部材である鏡板とベローズに着目し、設計を超える過大な圧力を受けた場合の座屈、座屈後変形、さらにバウンダリの貫通破損(バウンダリ機能喪失)までの挙動を検討した。研究は、2013年度に始まり、段階的に進められたが、最終段階として、新たに提案する破損クライテリアの鏡板、ベローズへの適用結果を示すものである。
Se concentration in concrete rubbleBanjarnahor, I. M.; Do, V.-K.; 古瀬 貴広; 太田 祐貴; 田中 康介
Journal of Radioanalytical and Nuclear Chemistry, 334(7), p.4997 - 5006, 2025/05
被引用回数:2 パーセンタイル:73.73(Chemistry, Analytical)
Se has been conventionally measured via radiometry. However, measuring
Se this way is difficult due to its low specific radioactivity. Moreover, the measurement is time-consuming and susceptible to the radioactive interferences from highly radioactive nuclides (
Sr,
Cs, etc.) coexisting in the samples. ICP-MS/MS is widely known as a powerful technique to quantify difficult-to-measure radionuclides, which can effectively eliminate the interferences using a collision/reaction cell. In this research, a novel HCl-free chemical separation method was developed for separating Se from concrete matrices, followed by the selective measurement of Se concentration via ICP-MS/MS.
Se was purified by stepwise chemical separation using anion exchange resin and activated alumina. The separation condition was optimized and evaluated. The chemical recovery of
85% was achieved.
Se concentration was determined via ICP-MS/MS at m/z = 79 using ammonia gas as the reaction gas, and possible interferences such as those from the
Br isobar and argon gas were effectively mitigated. A method limit of detection of 0.1 Bq g
was achieved for the concrete rubble samples, making it a reliable tool for determining
Se concentrations in concrete rubble collected from the Fukushima Daiichi Nuclear Power Station.
福田 航大; 小原 徹*; 須山 賢也
Nuclear Technology, 211(5), p.963 - 973, 2025/05
被引用回数:2 パーセンタイル:55.60(Nuclear Science & Technology)An application of the boiling water reactor (BWR) to an offshore floating nuclear power plant (OFNP) is discussed in Japan. The BWR-type OFNP has some challenges for practical use, although it has high economic efficiency because of downsizing and simplification. One challenge is understanding reactor kinetics under conditions specific to the marine environment. This study quantitatively clarifies the total and spatial changes in power when the BWR is inclined during regular operation. Therefore, the TRAC/RELAP Advanced Computational Engine (TRACE) and Purdue Advanced Reactor Core Simulator (PARCS) codes were used to perform a three-dimensional neutronics-thermal-hydraulics-coupled transient analysis. The calculation model is based on Peach Bottom II. This study clarifies the changing trend in total and local BWR power by inclination with simplified modeling and conditions. Reasons for such changes are discussed based on changes in several thermal-hydraulic parameters. The difference in BWR power against the inclinations is small. Thus, it was implied that the BWR-type OFNP is expected to have a stable power supply capability during natural disasters. Finally, requires further studies to support the obtained conclusions are discussed.
関 暁之; 近藤 佑樹; 橋立 竜太; 吉川 雅紀; 横山 賢治; 高屋 茂; 江沼 康弘; 羽様 平; 若井 隆純; 浅山 泰
Proceedings of 31st International Conference on Nuclear Engineering (ICONE31) (Internet), 7 Pages, 2024/11
Japan Atomic Energy Agency (JAEA) is developing ARKADIA (Advanced Reactor Knowledge- and AI-aided Design Integration Approach through the whole plant lifecycle) to meet the expectations for safe, economical, and sustainable carbon-free energy. The Knowledge Management System (KMS) included in ARKADIA consolidates technical information on Sodium-cooled Fast Reactor development obtained from "Monju" and other projects. Currently, several search functions are being developed in KMS. First, indexes are added to the documents. In addition, a search function has been enhanced to enable cross-search of all information registered in KMS. Furthermore, information retrieval using knowledge graphs is being developed to enhance information retrieval. This function can integrate rules, standards, interpretations, guidelines, design information, and related feasibility check information into a knowledge graph. Finally, milestones in KMS development and further enhancements are presented.
中村 勇気*; 小島 良洋*; 山下 拓哉; 下村 健太; 溝上 伸也
Proceedings of 14th International Topical Meeting on Nuclear Reactor Thermal-Hydraulics, Operation, and Safety (NUTHOS-14) (Internet), 12 Pages, 2024/08
At the Fukushima Daiichi Nuclear Power Plant accident, it has been reported that several units of containment vessel had failed, and large quantity of radionuclides had been released into the environment. However, the detailed accident progression of such a containment failure, which includes core melt, reactor vessel failure and following containment vessel behavior, has still large uncertainties. Especially for the unit 2 and 3, they had succeeded in the initial core cooling, but at last lost their cooling system and fell into severe accident to release the fission product into the environment. Nowadays, several information has been obtained by the internal inspection into the containment of the Fukushima Daiichi Nuclear Power Plants. To clarify the uncertainties in the accident scenario, considering the information and several insights already accustomed by previous research, the latest accident scenario in unit 2 and unit 3 of the Fukushima Daiichi Nuclear Power Plants accident are suggested and tested by the severe accident analysis code, MAAP in this study. It is shown that unit 2 and 3 both accident scenario would have resulted in the thermal stratification in suppression pool which encouraged the containment pressure response in the early phase of the accident. In addition, containment vessel leakage would have occurred and affected the containment depressurization.
関 暁之; 吉川 雅紀; 西野宮 良太*; 沖田 将一朗; 高屋 茂; Yan, X.
Nuclear Technology, 210(6), p.1003 - 1014, 2024/06
被引用回数:2 パーセンタイル:40.43(Nuclear Science & Technology)原子力プラントの安全な運転を支援するため、2種類のディープニューラルネットワーク(DNN)のシステムを構築した。一つは、原子力プラントの各種物理量についてシミュレーションよりも数桁少ない計算時間で推定するサロゲートシステム(SS)である。もう一つは、物理量から異常の原因となる外乱の状態を推定するシステム(ASIS)である。両システムとも、高温工学試験研究炉(HTTR)の挙動を様々なシナリオで再現することができる解析コード(ACCORD)から得られたデータを用いて学習を行った。DNNのモデルは、主要なハイパーパラメータを調整することにより構築された。これらの手順を経て、開発したシステムが高い精度で動作することを確認した。
Ayoub, A.*; Wainwright, Haruko*; Sansavini, G.*; Gauntt, R.*; 斎藤 公明
iScience (Internet), 27(4), p.109485_1 - 109485_15, 2024/04
被引用回数:17 パーセンタイル:84.27(Multidisciplinary Sciences)This paper presents a multidisciplinary analysis of the Fukushima Daiichi Nuclear Power Plant accident. Along with the latest observations and simulation studies, we synthesize the time-series and event progressions during the accident across multiple disciplines. We identify three key factors that exacerbated the consequences of the accident: (1) the failure of Unit 2 containment venting, (2) the insufficient integration of radiation measurements and meteorology data in the evacuation strategy, and (3) the limited risk assessment and emergency preparedness. We conclude with new research and development directions to improve the resilience of nuclear energy systems and communities, including (1) meteorology-informed proactive venting, (2) machine learning-enabled adaptive evacuation zones, and (3) comprehensive risk-informed emergency planning while leveraging the experience from responses to other disasters.
池内 宏知; 小山 真一
日本原子力学会誌ATOMO
, 66(2), p.74 - 78, 2024/02
東京電力福島第一原子力発電所(1F)からの着実な燃料デブリの取出しに向けて、性状未知の燃料デブリ試料(未知試料)の分析技術・体制の構築が喫緊の課題となっている。このため、性状既知のサンプル(模擬燃料デブリ)を用いた分析試験と専門家間の議論を通じて、分析結果の妥当性や誤差をもたらす要因など、分析精度の現状の到達レベルを知るとともに、その影響因子の把握と改善に向けた検討が進められている。本稿では、「核種・元素量」の分析・評価技術の基盤整備について、一端を紹介する。
Cs occurring near the Fukushima Dai-ichi Nuclear Power Plant太田 雅和; 高原 省五; 吉村 和也; 長久保 梓; 廣内 淳; 林 奈穂; 阿部 智久; 舟木 泰智; 永井 晴康
Journal of Environmental Radioactivity, 264, p.107198_1 - 107198_15, 2023/08
被引用回数:3 パーセンタイル:15.90(Environmental Sciences)福島第一原子力発電所(FDNPP)事故時に環境中に放出され、陸面に沈着した放射性核種について、大気中に再浮遊した
Csの吸引は現在における主要な被ばく経路の一つである。再浮遊では、風による土壌粒子の巻き上げが主なメカニズムとされてきた。一方、FDNPP事故後の研究から、帰宅困難区域(DRZ)などの農村部においては、真菌類による胞子放出が大気中
Cs濃度に影響を及ぼす可能性が示唆されてきた。本研究は、土壌粒子および真菌類胞子としての
Cs再浮遊を計算するモデルを開発し、これをDRZ内に適用することで、これら再浮遊過程の大気中濃度への影響評価を試みた。モデル計算の結果から、土壌粒子の再浮遊は冬から春に観測された大気中
Csの主要因となったものの、夏から秋に観測された高濃度を再現できないことが示された。真菌類からの胞子状
Csの放出を考慮することで、この夏から秋の高濃度事象は概ねモデルで再現された。解析結果から、真菌類胞子への
Csの蓄積と、農村部に特徴づけられる高い胞子放出率が夏から秋の大気中
Csに寄与している可能性が見出された。DRZ内には依然として未除染の森林が存在しているため、この真菌類胞子の大気中
Csへの寄与は今後将来も継続する可能性がある。
笛田 和希*; 小宮 樹*; 蓑毛 健太*; 堀江 憲路*; 竹原 真美*; 山崎 信哉*; 塩津 弘之; 大貫 敏彦*; Grambow, B.*; Law, G. T. W.*; et al.
Chemosphere, 328, p.138566_1 - 138566_12, 2023/07
被引用回数:7 パーセンタイル:41.64(Environmental Sciences)Fukushima Daiichi Nuclear Power Plant (FDNPP) derived radioactive Cs-rich microparticles (CsMPs) present a potential health risk through inhalation. Despite their occurrence in indoor environments impacted by the FDNPP accident, little is known about their prevalence. In this study, we quantitatively analyse the distribution and number of CsMPs in indoor dust samples collected from an elementary school located 2.8 km to the southwest of FDNPP. The school had remained untouched until 2016. Then, using a modified version of the autoradiography based "quantifying CsMPs (mQCP) method," we collected samples and determined the number of CsMPs and Cs radioactive fraction (RF) values of the microparticles (defined as total Cs activity from CsMPs / bulk Cs activity of entire sample). The numbers of CsMPs were determined to be 653 - 2570 particles/g and 296 - 1273 particles/g on the first and second floors of the school, respectively. The corresponding RFs ranged between 6.85 - 38.9 % and 4.48 - 6.61 %, respectively. The number of CsMPs and RF values in additional outdoor samples near the school building were and 23 - 63 particles/g and 1.14 - 1.61 %, respectively. The CsMPs were most abundant on the School's first floor near to the entrance, and the relative abundance was high near to the stairs on the second floor, indicating a likely CsMP dispersion path through the building. Additional wetting of the indoor samples combined with autoradiography revealed that indoor dusts had a distinct absence of intrinsic, soluble Cs species like CsOH. Combined, the results indicate that a significant amount of poorly soluble CsMPs were likely contained in initial radioactive airmass plumes from the FDNPP and that the microparticles could penetrate buildings. Clean-up plans for buildings / residential areas impacted by CsMP containing plumes, and monitoring of areas re-opened to the public, should take account of CsMPs in dusts.
鈴木 誠矢; 荒井 陽一; 岡村 信生; 渡部 雅之
Journal of Nuclear Science and Technology, 60(7), p.839 - 848, 2023/07
被引用回数:0 パーセンタイル:0.00(Nuclear Science & Technology)福島第一原子力発電所の事故で発生した燃料デブリは、溶融した核燃料物質と原子炉の構造材等で構成された酸化物が多くを占めているため、環境温度の変化により岩石のように劣化する可能性が高い。燃料デブリは10年以上水冷されているが、季節や昼夜の温度変化の影響を少なからず受けていることから、燃料デブリの経年変化挙動を評価するためには環境温度の変化を考慮することが不可欠である。仮に燃料デブリの劣化が進んでいる場合、微粉化した放射性物質が冷却水中に溶出して取出し作業に影響を及ぼす可能性がある。本研究では、環境温度の繰り返し変化がクラックの発生に与える影響に着目して、燃料デブリの模擬体を用いた加速試験を実施した。その結果、クラックは温度変化を重ねることで増加することを確認し、燃料デブリの簿擬態は熱膨張と収縮による応力により脆化することが判明した。燃料デブリの物理学的な劣化挙動は岩石や鉱物に類似していることが確認され、模擬燃料デブリと環境のモデルでクラックの増加挙動を予測することが可能となった。
久保 光太郎
Science and Technology of Nuclear Installations, 2023, p.7402217_1 - 7402217_12, 2023/06
被引用回数:2 パーセンタイル:27.37(Nuclear Science & Technology)Probabilistic risk assessment (PRA) is an effective methodology that could be used to improve the safety of nuclear power plants in a reasonable manner. Dynamic PRA, as an advanced PRA allows for more realistic and detailed analyses by handling time-dependent information. However, the applications of this method to practical problems are limited because it remains in the research and development stage. This study aimed to investigate the possibility of utilizing dynamic PRA in risk-informed decision-making. Specifically, the author performed an accident sequence precursor (ASP) analysis on the failure of emergency diesel generators that occurred at Unit 1 of the Tomari Nuclear Power Plant in Japan using dynamic PRA. The results were evaluated by comparison with the results of simplified classical PRA. The findings indicated that dynamic PRA may estimate lower risks compared with those obtained from classical PRA by reasonable modeling of alternating current power recovery. The author also showed that dynamic PRA can provide detailed information that cannot be obtained with classical PRA, such as uncertainty distribution of core damage timing and importance measure considering the system failure timing.
北垣 徹; Krasnov, V.*; 池田 篤史
Journal of Nuclear Materials, 576, p.154224_1 - 154224_14, 2023/04
被引用回数:10 パーセンタイル:57.34(Materials Science, Multidisciplinary)Nuclear fuel debris is a complex material containing a wide range of elements, compounds, and radiation. This complexity renders all the stages of the treatment of nuclear fuel debris extremely difficult and troublesome in the technical context. The whole treatment of nuclear fuel debris is also an extremely long-term process for tens of thousands of years, during which the aging of nuclear fuel debris is an unavoidable but critical issue. This applies to the decommissioning of the damaged reactors of the Fukushima Daiichi Nuclear Power Station (1F). This review article aims at collecting and summarizing the knowledge and information about the aging of materials containing nuclear fuels (fuel-containing materials) formed as a result of the accident at ChNPP-4 in the light of the decommissioning of 1F and assessing the potential effects of aging on the nuclear fuel debris remaining in the damaged 1F reactors.
長谷 竹晃; 相樂 洋*; 小菅 義広*; 能見 貴佳; 奥村 啓介
Journal of Nuclear Science and Technology, 60(4), p.460 - 472, 2023/04
被引用回数:1 パーセンタイル:9.64(Nuclear Science & Technology)This paper provides an overview of the applicability of the Differential Die-Away Self-Interrogation (DDSI) technique for quantification of spontaneous fissile nuclides in fuel debris at the Fukushima Daiichi Nuclear Power Plants. In this research, massive fuel debris stored in a canister was evaluated, and the void space of the canister was assumed to be filled with water for wet storage and air for dry storage. The composition of fuel debris was estimated based on elements such as the inventory in the reactor core and operation history. The simulation results show that for wet storage, the DDSI technique can properly evaluate the neutron leakage multiplication and quantify spontaneous fissile nuclides with a total measurement uncertainty (TMU) of approximately 8%. For dry storage, the known-alpha technique, which was previously established, can be applied to quantify spontaneous fissile nuclides with a TMU of approximately 4%. In both cases, the largest uncertainty factor is the variation in water content in the canister. In the case of wet storage, the uncertainty could be significantly increased in cases where the fuel debris is extremely unevenly distributed in the canister.
Dong, F.*; Chen, S.*; 出町 和之*; 吉川 雅紀; 関 暁之; 高屋 茂
Nuclear Engineering and Design, 404, p.112161_1 - 112161_15, 2023/04
被引用回数:39 パーセンタイル:99.31(Nuclear Science & Technology)To ensure nuclear safety, timely and accurate anomaly detection is of utmost importance in the daily condition monitoring of Nuclear Power Plants (NPPs), as any slight anomaly in a plant may result in an irreversible and serious accident, as well as high costs of maintenance and management. Nevertheless, due to the unique inherent attributes of anomalies, the difficulty of automatic detection in NPPs is increased. Previous model-driven anomaly detection approaches required skilled priori knowledge, leading to their limited usability. Commonly adopted deep learning-based data-driven anomaly detection approaches may not easily acquire the most relevant features when dealing with sensor data containing redundant information with uneven distribution of anomalies. To alleviate these issues, this paper propose an attention-based time series model for anomaly detection to ensure safety in NPPs. First, we employ one-dimension convolutional neural network (1D-CNN) backbone for feature extraction to preserve original inherent features of time series inputs. Subsequently, we originally adopt soft-attention mechanism to automatically extract the most relevant temporal features considering the specificity of anomaly detection in NPPs. The performance of the proposed model was experimentally validated on the High Temperature Gas-cooled Reactor (HTGR) anomaly case dataset simulated using the analytical code. The experimental results indicate that the proposed model was capable of detecting anomalies in NPPs with superior performance to the baseline model, while ensuring fast detection at short time steps.